[ { "id": "https://authors.library.caltech.edu/records/we1qr-hkc81", "eprint_id": 26027, "eprint_status": "archive", "datestamp": "2023-08-19 13:36:15", "lastmod": "2023-10-24 16:11:34", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Reidel-Marc-D", "name": { "family": "Reidel", "given": "Marc D." } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Timing Analysis of Cyclic Combinational Circuits", "ispublished": "unpub", "full_text_status": "public", "note": "This work is supported in part by a grant from the National Human Genome Research Institute (Grant no. P50 HG02370).\n\n
Accepted Version - etr060.pdf
", "abstract": "The accepted wisdom is that combinational circuits must have acyclic (i.e., loop-free or feed-forward) topologies. And yet simple examples suggest that this need not be so. In previous work, we advocated the design of cyclic combinational circuits (i.e., circuits with loops or feedback paths). We proposed a methodology for analyzing and synthesizing such circuits, with an emphasis on the optimization of area. \n\nIn this paper, we extend our methodology into the temporal realm. We characterize the true delay of cyclic circuits through symbolic event propagation in the floating mode of operation, according to the up-bounded inertial delay model. We present analysis results for circuits optimized with our program CYCLIFY. Some benchmark circuits were optimized significantly, with simultaneous improvements of up to 10% in the area and 25% in the delay.", "date": "2023-01-26", "date_type": "published", "publisher": "Caltech", "id_number": "CaltechPARADISE:2004.ETR060.1159", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2004.ETR060.1159", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format", "funders": { "items": [ { "agency": "NIH", "grant_number": "P50 HG02370" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr060.pdf", "url": "https://authors.library.caltech.edu/records/we1qr-hkc81/files/etr060.pdf" }, "pub_year": "2023", "author_list": "Reidel, Marc D. and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/zy6qg-qnq04", "eprint_id": 109572, "eprint_status": "archive", "datestamp": "2023-08-20 01:45:25", "lastmod": "2024-01-15 21:23:08", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Kilic-Kordag-Mehmet", "name": { "family": "Kilic", "given": "Kordag Mehmet" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Neural Networks Computations with DOMINATION Functions", "ispublished": "unpub", "full_text_status": "public", "note": "Submitted - etr151.pdf
", "abstract": "We study a new representation of neural networks based on DOMINATION functions. Specifically, we show that a threshold function can be computed by its variables connected via an unweighted bipartite graph to a universal gate computing a DOMINATION function. The DOMINATION function consists of fixed weights that are ascending powers of 2. We derive circuit-size upper and lower bounds for circuits with small weights that compute DOMINATION functions. Interestingly, the circuit-size bounds are dependent on the sparsity of the\nbipartite graph. In particular, functions with sparsity 1 (like the EQUALITY function) can be implemented by small-size constant-weight circuits.", "date": "2021-06-25", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20210624-214748102", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20210624-214748102", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr151.pdf", "url": "https://authors.library.caltech.edu/records/zy6qg-qnq04/files/etr151.pdf" }, "pub_year": "2021", "author_list": "Kilic, Kordag Mehmet and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/gyvxr-1zd71", "eprint_id": 109575, "eprint_status": "archive", "datestamp": "2023-08-20 01:45:29", "lastmod": "2024-01-15 21:23:10", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Sima-Jin", "name": { "family": "Sima", "given": "Jin" }, "orcid": "0000-0003-4588-9790" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Trace Reconstruction with Bounded Edit Distance", "ispublished": "unpub", "full_text_status": "public", "note": "Submitted - etr152.pdf
", "abstract": "The trace reconstruction problem studies the number of noisy samples needed to recover an unknown string x \u2208 {0, 1}^n with high probability, where the samples are independently obtained by passing x through a random deletion channel with deletion probability p. The problem is receiving significant attention recently due to its applications in DNA sequencing and DNA storage. Yet, there is still an exponential gap between upper and lower bounds for the trace reconstruction problem. In this paper we study the trace reconstruction problem when x is confined to an edit distance ball of radius k, which is essentially equivalent to distinguishing two strings with edit distance at most k. It is shown that n\nO(k) samples suffice to achieve this task with high probability.", "date": "2021-06-25", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20210624-215307865", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20210624-215307865", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr152.pdf", "url": "https://authors.library.caltech.edu/records/gyvxr-1zd71/files/etr152.pdf" }, "pub_year": "2021", "author_list": "Sima, Jin and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/dp1g8-cv171", "eprint_id": 109569, "eprint_status": "archive", "datestamp": "2023-08-19 23:42:57", "lastmod": "2024-01-15 21:23:04", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Mazaheri-Bijan", "name": { "family": "Mazaheri", "given": "Bijan" } }, { "id": "Jain-Siddharth", "name": { "family": "Jain", "given": "Siddharth" }, "orcid": "0000-0002-9164-6119" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Robust Correction of Sampling Bias Using Cumulative Distribution Functions", "ispublished": "unpub", "full_text_status": "public", "note": "This work is supported by supported by the National Science Foundation Graduate Research Fellowship under Grant No. DGE-1745301, NSF Grant No. CCF-1717884 and The Carver Mead New Adventure Fund.\n\nSubmitted - etr149.pdf
", "abstract": "Varying domains and biased datasets can lead to differences between the training and the target distributions, known as covariate shift. Current approaches for alleviating this often rely on estimating the ratio of training and target probability density functions. These techniques require parameter tuning and can be unstable across different datasets. We present a new method for handling covariate shift using the empirical cumulative distribution function estimates of the target distribution by a rigorous generalization of a recent idea proposed by Vapnik and Izmailov. Further, we show experimentally that our method is more robust in its predictions, is not reliant on parameter tuning and shows similar classification performance compared to the current state-of-the-art techniques on synthetic and real datasets.", "date": "2021-06-24", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20210624-211933517", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20210624-211933517", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "funders": { "items": [ { "agency": "NSF Graduate Research Fellowship", "grant_number": "DGE-1745301" }, { "agency": "NSF", "grant_number": "CCF-1717884" }, { "agency": "Carver Mead New Adventures Fund" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr149.pdf", "url": "https://authors.library.caltech.edu/records/dp1g8-cv171/files/etr149.pdf" }, "pub_year": "2021", "author_list": "Mazaheri, Bijan; Jain, Siddharth; et el." }, { "id": "https://authors.library.caltech.edu/records/bkec1-w3e38", "eprint_id": 109570, "eprint_status": "archive", "datestamp": "2023-08-20 01:45:21", "lastmod": "2024-01-15 21:23:07", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Mazaheri-Bijan", "name": { "family": "Mazaheri", "given": "Bijan" } }, { "id": "Jain-Siddharth", "name": { "family": "Jain", "given": "Siddharth" }, "orcid": "0000-0002-9164-6119" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Synthesizing New Expertise via Collaboration", "ispublished": "unpub", "full_text_status": "public", "note": "Submitted - etr150.pdf
", "abstract": "Consider a set of classes and an uncertain input. Suppose, we do not have access to data and only have knowledge of perfect experts between a few classes in the set. What constitutes a consistent set of opinions? How can we use this to predict the opinions of experts on missing sub-domains? In this paper, we define a framework to analyze this problem. In particular, we define an expert graph where vertices represent classes and edges represent binary experts on the topics of their vertices. We derive necessary conditions for an expert graph to be valid. Further, we show that these conditions are also sufficient if the graph is a cycle, which can yield unintuitive results. Using these conditions, we provide an algorithm to obtain upper and lower bounds on the weights of unknown edges in an expert graph.", "date": "2021-06-24", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20210624-214158214", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20210624-214158214", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr150.pdf", "url": "https://authors.library.caltech.edu/records/bkec1-w3e38/files/etr150.pdf" }, "pub_year": "2021", "author_list": "Mazaheri, Bijan; Jain, Siddharth; et el." }, { "id": "https://authors.library.caltech.edu/records/6k379-qfk69", "eprint_id": 103102, "eprint_status": "archive", "datestamp": "2023-08-19 21:23:33", "lastmod": "2024-01-15 03:01:40", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Jain-Siddharth", "name": { "family": "Jain", "given": "Siddharth" }, "orcid": "0000-0002-9164-6119" }, { "id": "Farnoud-Farzad", "name": { "family": "Farnoud (Hassanzadeh)", "given": "Farzad" }, "orcid": "0000-0002-8684-4487" }, { "id": "Schwartz-Moshe", "name": { "family": "Schwartz", "given": "Moshe" }, "orcid": "0000-0002-1449-0026" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Coding for Optimized Writing Rate in DNA Storage", "ispublished": "unpub", "full_text_status": "public", "note": "This work was supported in part by a United States\u2013Israel Binational Science Foundation (BSF) under grant no. 2017652, and by NSF grants under grant nos. CCF-1816409, CCF-1755773, CCF-1816965, and CCF-1717884.\n\nSubmitted - etr148.pdf
", "abstract": "A method for encoding information in DNA sequences is described. The method is based on the precision-resolution framework, and is aimed to work in conjunction with a recently suggested terminator-free template independent DNA synthesis method. The suggested method optimizes the amount of information bits per synthesis time unit, namely, the writing rate. Additionally, the encoding scheme studied here takes into account the existence of multiple copies of the DNA sequence, which are independently distorted. Finally, quantizers for various run-length distributions are designed.", "date": "2020-05-11", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20200511-120246633", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20200511-120246633", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "funders": { "items": [ { "agency": "Binational Science Foundation (USA-Israel)", "grant_number": "2017652" }, { "agency": "NSF", "grant_number": "CCF-1816409" }, { "agency": "NSF", "grant_number": "CCF-1755773" }, { "agency": "NSF", "grant_number": "CCF-1816965" }, { "agency": "NSF", "grant_number": "CCF-1717884" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr148.pdf", "url": "https://authors.library.caltech.edu/records/6k379-qfk69/files/etr148.pdf" }, "pub_year": "2020", "author_list": "Jain, Siddharth; Farnoud (Hassanzadeh), Farzad; et el." }, { "id": "https://authors.library.caltech.edu/records/xp0ns-zr574", "eprint_id": 102790, "eprint_status": "archive", "datestamp": "2023-08-19 20:46:10", "lastmod": "2024-01-15 03:01:21", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Raviv-Netanel", "name": { "family": "Raviv", "given": "Netanel" }, "orcid": "0000-0002-1686-1994" }, { "id": "Jain-Siddharth", "name": { "family": "Jain", "given": "Siddharth" }, "orcid": "0000-0002-9164-6119" }, { "id": "Upadhyaya-Pulakesh", "name": { "family": "Upadhyaya", "given": "Pulakesh" }, "orcid": "0000-0003-1054-1380" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" }, { "id": "Jiang-Anxiao-Andrew", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } } ] }, "title": "CodNN - Robust Neural Networks From Coded Classification", "ispublished": "unpub", "full_text_status": "public", "note": "Submitted - etr147.pdf
", "abstract": "Deep Neural Networks (DNNs) are a revolutionary force in the ongoing information revolution, and yet their intrinsic properties remain a mystery. In particular, it is widely known that DNNs are highly sensitive to noise, whether adversarial or random. This poses a fundamental challenge for hardware implementations of DNNs, and for their deployment in critical applications such as autonomous driving. \n\nIn this paper we construct robust DNNs via error correcting codes. By our approach, either the data or internal layers of the DNN are coded with error correcting codes, and successful computation under noise is guaranteed. Since DNNs can be seen as a layered concatenation of classification tasks, our research begins with the core task of classifying noisy coded inputs, and progresses towards robust DNNs. \n\nWe focus on binary data and linear codes. Our main result is that the prevalent parity code can guarantee robustness for a large family of DNNs, which includes the recently popularized binarized neural networks. Further, we show that the coded classification problem has a deep connection to Fourier analysis of Boolean functions. \n\nIn contrast to existing solutions in the literature, our results do not rely on altering the training process of the DNN, and provide mathematically rigorous guarantees rather than experimental evidence.", "date": "2020-04-27", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20200427-091132325", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20200427-091132325", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr147.pdf", "url": "https://authors.library.caltech.edu/records/xp0ns-zr574/files/etr147.pdf" }, "pub_year": "2020", "author_list": "Raviv, Netanel; Jain, Siddharth; et el." }, { "id": "https://authors.library.caltech.edu/records/c66kf-a5m87", "eprint_id": 102433, "eprint_status": "archive", "datestamp": "2023-08-19 18:09:45", "lastmod": "2024-01-15 03:01:08", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Sima-Jin", "name": { "family": "Sima", "given": "Jin" }, "orcid": "0000-0003-4588-9790" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Optimal k-Deletion Correcting Codes", "ispublished": "unpub", "full_text_status": "public", "note": "This work was presented in part at the IEEE International Symposium on Information Theory, Paris, France, July 2019.\n\nSubmitted - etr146.pdf
", "abstract": "Levenshtein introduced the problem of constructing k-deletion correcting codes in 1966, proved that the optimal redundancy\nof those codes is O(k log N), and proposed an optimal redundancy single-deletion correcting code (using the so-called VT\nconstruction). However, the problem of constructing optimal redundancy k-deletion correcting codes remained open. Our key\ncontribution is a solution to this longstanding open problem. We present a k-deletion correcting code that has redundancy 8k log n+\no(log n) and encoding/decoding algorithms of complexity O(n^(2k+1)) for constant k.", "date": "2020-04-09", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20200409-105733198", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20200409-105733198", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr146.pdf", "url": "https://authors.library.caltech.edu/records/c66kf-a5m87/files/etr146.pdf" }, "pub_year": "2020", "author_list": "Sima, Jin and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/ejevm-acb46", "eprint_id": 93009, "eprint_status": "archive", "datestamp": "2023-08-19 13:51:20", "lastmod": "2024-01-14 21:29:00", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Raviv-N", "name": { "family": "Raviv", "given": "Netanel" }, "orcid": "0000-0002-1686-1994" }, { "id": "Yu-Qian", "name": { "family": "Yu", "given": "Qian" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" }, { "id": "Avestimehr-S", "name": { "family": "Avestimehr", "given": "Salman" } } ] }, "title": "Download and Access Trade-offs in Lagrange Coded Computing", "ispublished": "unpub", "full_text_status": "public", "note": "Submitted - etr144.pdf
", "abstract": "Lagrange Coded Computing (LCC) is a recently\nproposed technique for resilient, secure, and private computation\nof arbitrary polynomials in distributed environments. By\nmapping such computations to composition of polynomials, LCC\nallows the master node to complete the computation by accessing\na minimal number of workers and downloading all of their\ncontent, thus providing resiliency to the remaining stragglers.\nHowever, in the most common case in which the number of\nstragglers is less than in the worst case scenario, much of the\ncomputational power of the system remains unexploited. To\namend this issue, in this paper we expand LCC by studying a\nfundamental trade-off between download and access, and present\ntwo contributions. In the first contribution, it is shown that\nwithout any modification to the encoding process, the master\ncan decode the computations by accessing a larger number of\nnodes, however downloading less information from each node in\ncomparison with LCC (i.e., trading access for download). This\nscheme relies on decoding a particular polynomial in the ideal\nthat is generated by the polynomials of interest, a technique we\ncall Ideal Decoding. This new scheme also improves LCC in the\nsense that for systems with adversaries, the overall downloaded\nbandwidth is smaller than in LCC. In the second contribution\nwe study a real-time model of this trade-off, in which the data\nfrom the workers is downloaded sequentially. By clustering nodes\nof similar delays and encoding the function with Universally\nDecodable Matrices, the master can decode once sufficient data is\ndownloaded from every cluster, regardless of the internal delays\nwithin that cluster. This allows the master to utilize the partial\nwork that is done by stragglers, rather than to ignore it, a feature\nthat most past works in coded computing are lacking.", "date": "2019-02-20", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20190220-123432908", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20190220-123432908", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr144.pdf", "url": "https://authors.library.caltech.edu/records/ejevm-acb46/files/etr144.pdf" }, "pub_year": "2019", "author_list": "Raviv, Netanel; Yu, Qian; et el." }, { "id": "https://authors.library.caltech.edu/records/wxrqy-7c610", "eprint_id": 92820, "eprint_status": "archive", "datestamp": "2023-08-19 14:15:01", "lastmod": "2023-10-20 16:29:23", "type": "article", "metadata_visibility": "show", "creators": { "items": [ { "id": "Farnoud-Farzad", "name": { "family": "Farnoud (Hassanzadeh)", "given": "Farzad" }, "orcid": "0000-0002-8684-4487" }, { "id": "Schwartz-Moshe", "name": { "family": "Schwartz", "given": "Moshe" }, "orcid": "0000-0002-1449-0026" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Estimation of duplication history under a stochastic model for tandem repeats", "ispublished": "pub", "full_text_status": "public", "note": "\u00a9 2019 The Author(s). This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The Creative Commons Public Domain Dedication waiver(http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated. \n\nReceived: 27 July 2018; Accepted: 3 January 2019; Published: 6 February 2019. \n\nThe authors would like to thank Han Mao Kiah for helpful discussions related to Lemma 1. Furthermore, the authors would like to thank anonymous reviewers for their insightful comments and valuable suggestions, which helped us improve the paper. \n\nThis research was supported by National Science Foundation grants CCF-1317694 and CCF-1755773, and by a United States \u2013 Israel Binational Science Foundation (BSF) grant no. 2017652. \n\nAvailability of data and materials: The datasets analyzed in the current study are available from the Tandem Repeat Database (https://tandem.bu.edu/cgi-bin/trdb/trdb.exe) [28] under organism: Homo sapiens HG38. \n\nAuthors' contributions: All authors contributed to the theoretical analysis and the development of the estimation method. FF performed the data analysis and FF and MS prepared the manuscript. All authors read and approved the final manuscript. \n\nEthics approval and consent to participate: Not applicable. \n\nConsent for publication: Not applicable. \n\nThe authors declare that they have no competing interests.\n\nPublished - s12859-019-2603-1.pdf
Supplemental Material - 12859_2019_2603_MOESM1_ESM.pdf
", "abstract": "Background: Tandem repeat sequences are common in the genomes of many organisms and are known to cause important phenomena such as gene silencing and rapid morphological changes. Due to the presence of multiple copies of the same pattern in tandem repeats and their high variability, they contain a wealth of information about the mutations that have led to their formation. The ability to extract this information can enhance our understanding of evolutionary mechanisms. \n\nResults: We present a stochastic model for the formation of tandem repeats via tandem duplication and substitution mutations. Based on the analysis of this model, we develop a method for estimating the relative mutation rates of duplications and substitutions, as well as the total number of mutations, in the history of a tandem repeat sequence. We validate our estimation method via Monte Carlo simulation and show that it outperforms the state-of-the-art algorithm for discovering the duplication history. We also apply our method to tandem repeat sequences in the human genome, where it demonstrates the different behaviors of micro- and mini-satellites and can be used to compare mutation rates across chromosomes. It is observed that chromosomes that exhibit the highest mutation activity in tandem repeat regions are the same as those thought to have the highest overall mutation rates. However, unlike previous works that rely on comparing human and chimpanzee genomes to measure mutation rates, the proposed method allows us to find chromosomes with the highest mutation activity based on a single genome, in essence by comparing (approximate) copies of the pattern in tandem repeats. \n\nConclusion: The prevalence of tandem repeats in most organisms and the efficiency of the proposed method enable studying various aspects of the formation of tandem repeats and the surrounding sequences in a wide range of settings.", "date": "2019-02-06", "date_type": "published", "publication": "BMC Bioinformatics", "volume": "20", "publisher": "BioMed Central", "pagerange": "Art. No. 64", "id_number": "CaltechAUTHORS:20190211-084750757", "issn": "1471-2105", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20190211-084750757", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "funders": { "items": [ { "agency": "NSF", "grant_number": "CCF-1317694" }, { "agency": "NSF", "grant_number": "CCF-1755773" }, { "agency": "Binational Science Foundation (USA-Israel)", "grant_number": "2017652" } ] }, "other_numbering_system": { "items": [ { "id": "etr145", "name": "PARADISE" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "doi": "10.1186/s12859-019-2603-1", "primary_object": { "basename": "12859_2019_2603_MOESM1_ESM.pdf", "url": "https://authors.library.caltech.edu/records/wxrqy-7c610/files/12859_2019_2603_MOESM1_ESM.pdf" }, "related_objects": [ { "basename": "s12859-019-2603-1.pdf", "url": "https://authors.library.caltech.edu/records/wxrqy-7c610/files/s12859-019-2603-1.pdf" } ], "pub_year": "2019", "author_list": "Farnoud (Hassanzadeh), Farzad; Schwartz, Moshe; et el." }, { "id": "https://authors.library.caltech.edu/records/gvax7-79g91", "eprint_id": 90087, "eprint_status": "archive", "datestamp": "2023-08-19 11:37:58", "lastmod": "2024-01-14 21:08:05", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Sima-Jin", "name": { "family": "Sima", "given": "Jin" }, "orcid": "0000-0003-4588-9790" }, { "id": "Raviv-N", "name": { "family": "Raviv", "given": "Netanel" }, "orcid": "0000-0002-1686-1994" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "On Coding over Sliced Information", "ispublished": "unpub", "full_text_status": "public", "note": "Submitted - etr143.pdf
", "abstract": "The interest in channel models in which the data is sent as an unordered set of binary strings has increased lately, due to emerging applications in DNA storage, among others. In this paper we analyze the minimal redundancy of binary codes for this channel under substitution errors, and provide several constructions, some of which are shown to be asymptotically optimal. The surprising result in this paper is that while the information vector is sliced into a set of unordered strings, the amount of redundant bits that are required to correct errors is asymptotically equal to the amount required in the classical error correcting paradigm.", "date": "2018-10-05", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20181002-162910265", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20181002-162910265", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "other_numbering_system": { "items": [ { "id": "etr-143", "name": "PARADISE" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr143.pdf", "url": "https://authors.library.caltech.edu/records/gvax7-79g91/files/etr143.pdf" }, "pub_year": "2018", "author_list": "Sima, Jin; Raviv, Netanel; et el." }, { "id": "https://authors.library.caltech.edu/records/f8j16-pfh10", "eprint_id": 88948, "eprint_status": "archive", "datestamp": "2023-08-19 10:44:53", "lastmod": "2024-01-14 20:40:06", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Elishco-Ohad", "name": { "family": "Elishco", "given": "Ohad" }, "orcid": "0000-0002-8551-1592" }, { "id": "Farnoud-Farzad", "name": { "family": "Farnoud (Hassanzadeh)", "given": "Farzad" }, "orcid": "0000-0002-8684-4487" }, { "id": "Schwartz-Moshe", "name": { "family": "Schwartz", "given": "Moshe" }, "orcid": "0000-0002-1449-0026" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "The Capacity of Some P\u00f3lya String Models", "ispublished": "unpub", "full_text_status": "public", "keywords": "DNA storage, string-duplication systems, capacity, P\u00f3lya string models", "note": "The material in this paper was presented in part at the 2016 IEEE International Symposium on Information Theory.\n\nSubmitted - etr142.pdf
", "abstract": "We study random string-duplication systems, which we call P\u00f3lya string models. These are motivated by DNA storage in living organisms, and certain random mutation processes that affect their genome. Unlike previous works that study the combinatorial capacity of string-duplication systems, or various string statistics, this work provides exact capacity or bounds on it, for several probabilistic models. In particular, we study the capacity of noisy string-duplication systems, including the tandem-duplication, end-duplication, and interspersed-duplication systems. Interesting connections are drawn between some systems and the signature of random permutations, as well as to the beta distribution common in population genetics.", "date": "2018-08-20", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20180820-100255874", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20180820-100255874", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "other_numbering_system": { "items": [ { "id": "etr-142", "name": "PARADISE" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr142.pdf", "url": "https://authors.library.caltech.edu/records/f8j16-pfh10/files/etr142.pdf" }, "pub_year": "2018", "author_list": "Elishco, Ohad; Farnoud (Hassanzadeh), Farzad; et el." }, { "id": "https://authors.library.caltech.edu/records/yfm4q-xt198", "eprint_id": 87638, "eprint_status": "archive", "datestamp": "2023-08-19 00:54:40", "lastmod": "2024-01-14 20:20:08", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Huang-Wentao", "name": { "family": "Huang", "given": "Wentao" }, "orcid": "0000-0003-0963-3624" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Secret Sharing with Optimal Decoding and Repair Bandwidth", "ispublished": "unpub", "full_text_status": "public", "note": "Draft - etr135.pdf
", "abstract": "This paper studies the communication efficiency of threshold secret sharing schemes. We construct a family of Shamir's schemes with asymptotically optimal decoding bandwidth for arbitrary parameters. We also construct a family of secret sharing schemes with both optimal decoding bandwidth and optimal repair bandwidth for arbitrary parameters. The construction also leads to a family of regenerating codes allowing centralized repair of multiple node failures with small sub-packetization.", "date": "2018-07-09", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20180709-102239656", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20180709-102239656", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "other_numbering_system": { "items": [ { "id": "etr-135", "name": "PARADISE" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr135.pdf", "url": "https://authors.library.caltech.edu/records/yfm4q-xt198/files/etr135.pdf" }, "pub_year": "2018", "author_list": "Huang, Wentao and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/j9nc6-ns538", "eprint_id": 87637, "eprint_status": "archive", "datestamp": "2023-08-19 00:54:35", "lastmod": "2024-01-14 20:20:06", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Huang-Wentao", "name": { "family": "Huang", "given": "Wentao" }, "orcid": "0000-0003-0963-3624" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Secure RAID Schemes from EVENODD and STAR Codes", "ispublished": "unpub", "full_text_status": "public", "note": "Submitted - etr136.pdf
", "abstract": "We study secure RAID, i.e., low-complexity schemes to store information in a distributed manner that is resilient to node failures and resistant to node eavesdropping. We describe a technique to shorten the secure EVENODD scheme in [6], which can optimally tolerate 2 node failures and 2 eavesdropping nodes. The shortening technique allows us to obtain secure EVENODD schemes of arbitrary lengths, which is important for practical application. We also construct a new secure RAID scheme from the STAR code. The scheme can tolerate 3 node failures and 3 eavesdropping nodes with optimal encoding/decoding and random access complexity.", "date": "2018-07-09", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20180709-101600551", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20180709-101600551", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "other_numbering_system": { "items": [ { "id": "etr-136", "name": "PARADISE" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr136.pdf", "url": "https://authors.library.caltech.edu/records/j9nc6-ns538/files/etr136.pdf" }, "pub_year": "2018", "author_list": "Huang, Wentao and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/v820p-vn536", "eprint_id": 87639, "eprint_status": "archive", "datestamp": "2023-08-19 09:32:05", "lastmod": "2024-01-14 20:20:11", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Sima-Jin", "name": { "family": "Sima", "given": "Jin" }, "orcid": "0000-0003-4588-9790" }, { "id": "Raviv-N", "name": { "family": "Raviv", "given": "Netanel" }, "orcid": "0000-0002-1686-1994" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Two Deletion Correcting Codes from Indicator Vectors", "ispublished": "unpub", "full_text_status": "public", "note": "The work was presented in part at the IEEE International Symposium on Information Theory, July 2018. The work was supported in part by NSF grant CCF-1717884. The work of Netanel Raviv was supported in part by the postdoctoral fellowship of the Center for the Mathematics of Information (CMI), Caltech, and in part by the Lester-Deutsch postdoctoral fellowship.\n\nSubmitted - etr141.pdf
", "abstract": "Construction of capacity achieving deletion correcting codes has been a baffling challenge for decades. A recent breakthrough by Brakensiek et al., alongside novel applications in DNA storage, have reignited the interest in this longstanding open problem. In spite of recent advances, the amount of redundancy in existing codes is still orders of magnitude away from being optimal. In this paper, a novel approach for constructing binary two-deletion correcting codes is proposed. By this approach, parity symbols are computed from indicator vectors (i.e., vectors that indicate the positions of certain patterns) of the encoded message, rather than from the message itself. Most interestingly, the parity symbols and the proof of correctness are a direct generalization of their counterparts in the Varshamov-Tenengolts construction. Our techniques require 7 log(n) + o(log(n) redundant bits to encode an n-bit message, which is near-optimal.", "date": "2018-07-09", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20180709-102730008", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20180709-102730008", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "funders": { "items": [ { "agency": "NSF", "grant_number": "CCF-1717884" }, { "agency": "Center for the Mathematics of Information, Caltech" }, { "agency": "Lester-Deutsch postdoctoral fellowship" } ] }, "other_numbering_system": { "items": [ { "id": "etr-141", "name": "PARADISE" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr141.pdf", "url": "https://authors.library.caltech.edu/records/v820p-vn536/files/etr141.pdf" }, "pub_year": "2018", "author_list": "Sima, Jin; Raviv, Netanel; et el." }, { "id": "https://authors.library.caltech.edu/records/msxyd-8x553", "eprint_id": 85207, "eprint_status": "archive", "datestamp": "2023-08-19 07:37:58", "lastmod": "2023-10-18 17:58:05", "type": "book_section", "metadata_visibility": "show", "creators": { "items": [ { "id": "Zuck-A", "name": { "family": "Zuck", "given": "Aviad" } }, { "id": "Li-Yue", "name": { "family": "Li", "given": "Yue" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" }, { "id": "Porter-D-E", "name": { "family": "Porter", "given": "Donald E." } }, { "id": "Tsafrir-D", "name": { "family": "Tsafrir", "given": "Dan" } } ] }, "title": "Stash in a Flash", "ispublished": "unpub", "full_text_status": "public", "note": "\u00a9 2018 USENIX.\n\nWe thank our shepherd and the anonymous reviewers for their insightful comments on earlier drafts of the work. This research was supported by Grant 2014621 from the United States-Israel Binational Science Foundation (BSF), by Grant CNS-1526707 from the United States National Science Foundation (NSF), and VMware. This work was done in part while Porter was at Stony Brook University.\n\nPublished - etr140.pdf
", "abstract": "Encryption is a useful tool to protect data confidentiality. Yet it is still challenging to hide the very presence of encrypted, secret data from a powerful adversary. This paper presents a new technique to hide data in flash by manipulating the voltage level of pseudo-randomlyselected flash cells to encode two bits (rather than one) in the cell. In this model, we have one \"public\" bit interpreted using an SLC-style encoding, and extract a private bit using an MLC-style encoding. The locations of cells that encode hidden data is based on a secret key known only to the hiding user.\n\nIntuitively, this technique requires that the voltage level in a cell encoding data must be (1) not statistically distinguishable from a cell only storing public data, and (2) the user must be able to reliably read the hidden data from this cell. Our key insight is that there is a wide enough variation in the range of voltage levels in a typical flash device to obscure the presence of fine-grained changes to a small fraction of the cells, and that the variation is wide enough to support reliably re-reading hidden data. We demonstrate that our hidden data and underlying voltage manipulations go undetected by support vector machine based supervised learning which performs similarly to a random guess. The error rates of our scheme are low enough that the data is recoverable months after being stored. Compared to prior work, our technique provides 24x and 50x higher encoding and decoding throughput and doubles the capacity, while being 37x more power efficient.", "date": "2018-02", "date_type": "published", "publisher": "Advanced Computing Systems Association", "pagerange": "169-185", "id_number": "CaltechAUTHORS:20180308-133517936", "isbn": "978-1-931971-42-3", "book_title": "16th USENIX Conference on File and Storage Technologies", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20180308-133517936", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "funders": { "items": [ { "agency": "Binational Science Foundation (USA-Israel)", "grant_number": "2014621" }, { "agency": "NSF", "grant_number": "CNS-1526707" } ] }, "other_numbering_system": { "items": [ { "id": "etr-140", "name": "PARADISE" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr140.pdf", "url": "https://authors.library.caltech.edu/records/msxyd-8x553/files/etr140.pdf" }, "pub_year": "2018", "author_list": "Zuck, Aviad; Li, Yue; et el." }, { "id": "https://authors.library.caltech.edu/records/cs627-f8728", "eprint_id": 84120, "eprint_status": "archive", "datestamp": "2023-08-19 07:18:07", "lastmod": "2024-01-14 19:15:43", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Jain-Siddharth", "name": { "family": "Jain", "given": "Siddharth" }, "orcid": "0000-0002-9164-6119" }, { "id": "Raviv-N", "name": { "family": "Raviv", "given": "Netanel" }, "orcid": "0000-0002-1686-1994" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Attaining the 2nd Chargaff Rule by Tandem Duplications", "ispublished": "unpub", "full_text_status": "public", "keywords": "reverse complement, inversion symmetry, balanced and unbalanced sequences, duplications", "note": "This work was supported in part by the NSF Expeditions in Computing Program - The Molecular Programming Project. The work of Netanel Raviv was supported in part by the postdoctoral fellowship of the Center for the Mathematics of Information (CMI), Caltech, and in part by the Lester-Deutsch postdoctoral fellowship.\n\nSubmitted - etr138.pdf
", "abstract": "Erwin Chargaff in 1950 made an experimental observation that the count of A is equal to the count of T and the count of C is equal to the count of G in DNA. This observation played a crucial rule in the discovery of the double stranded helix structure by Watson and Crick. However, this symmetry was also observed in single stranded DNA. This phenomenon was termed as 2nd Chargaff Rule. This symmetry has been verified experimentally in genomes of several different species not only for mononucleotides but also for reverse complement pairs of larger lengths up to a small error. While the symmetry in double stranded DNA is related to base pairing, and replication mechanisms, the symmetry in a single stranded DNA is still a mystery in its function and source. In this work, we define a sequence generation model based on reverse complement tandem duplications. We show that this model generates sequences that satisfy the 2nd Chargaff Rule even when the duplication lengths are very small when compared to the length of sequences. We also provide estimates on the number of generations that are needed by this model to generate sequences that satisfy 2nd Chargaff Rule. We provide theoretical bounds on the disruption in symmetry for different values of duplication lengths under this model. Moreover, we experimentally compare the disruption in the symmetry incurred by our model with what is observed in human genome data.", "date": "2018-01-05", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20180105-092230028", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20180105-092230028", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "funders": { "items": [ { "agency": "NSF" }, { "agency": "Center for the Mathematics of Information, Caltech" }, { "agency": "Lester-Deutsch postdoctoral fellowship" } ] }, "other_numbering_system": { "items": [ { "id": "ETR-38", "name": "PARADISE" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr138.pdf", "url": "https://authors.library.caltech.edu/records/cs627-f8728/files/etr138.pdf" }, "pub_year": "2018", "author_list": "Jain, Siddharth; Raviv, Netanel; et el." }, { "id": "https://authors.library.caltech.edu/records/9wjw1-zhb03", "eprint_id": 84351, "eprint_status": "archive", "datestamp": "2023-08-21 22:30:35", "lastmod": "2023-10-18 16:09:05", "type": "article", "metadata_visibility": "show", "creators": { "items": [ { "id": "Wilhelm-Daniel", "name": { "family": "Wilhelm", "given": "Daniel" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" }, { "id": "Qian-Lulu", "name": { "family": "Qian", "given": "Lulu" }, "orcid": "0000-0003-4115-2409" } ] }, "title": "Probabilistic switching circuits in DNA", "ispublished": "pub", "full_text_status": "public", "keywords": "molecular programming; DNA strand displacement circuits; stochasticity; digital and analog computation", "note": "\u00a9 2018 National Academy of Sciences. This open access article is distributed under Creative Commons Attribution-NonCommercial-NoDerivatives License 4.0 (CC BY-NC-ND). \n\nEdited by David Baker, University of Washington, Seattle, WA, and approved December 22, 2017 (received for review September 10, 2017). Published ahead of print January 16, 2018. \n\nWe thank D. Y. Zhang and E. Winfree for discussions. D.W., J.B., and L.Q. were supported by an NSF Expedition in Computing grant (0832824). L.Q. was also supported by a Career Award at the Scientific Interface from the Burroughs Wellcome Fund (1010684) and a Faculty Early Career Development Award from the NSF (1351081). \n\nAuthor contributions: J.B. and L.Q. designed research; D.W. and L.Q. performed research; D.W. and L.Q. analyzed data; and D.W., J.B., and L.Q. wrote the paper. \n\nThe authors declare no conflict of interest. \n\nThis article is a PNAS Direct Submission. \n\nThis article contains supporting information online at www.pnas.org/lookup/suppl/doi:10.1073/pnas.1715926115/-/DCSupplemental.\n\nPublished - 903.full.pdf
Supplemental Material - pnas.1715926115.sapp.pdf
", "abstract": "A natural feature of molecular systems is their inherent stochastic behavior. A fundamental challenge related to the programming of molecular information processing systems is to develop a circuit architecture that controls the stochastic states of individual molecular events. Here we present a systematic implementation of probabilistic switching circuits, using DNA strand displacement reactions. Exploiting the intrinsic stochasticity of molecular interactions, we developed a simple, unbiased DNA switch: An input signal strand binds to the switch and releases an output signal strand with probability one-half. Using this unbiased switch as a molecular building block, we designed DNA circuits that convert an input signal to an output signal with any desired probability. Further, this probability can be switched between 2^n different values by simply varying the presence or absence of n distinct DNA molecules. We demonstrated several DNA circuits that have multiple layers and feedback, including a circuit that converts an input strand to an output strand with eight different probabilities, controlled by the combination of three DNA molecules. These circuits combine the advantages of digital and analog computation: They allow a small number of distinct input molecules to control a diverse signal range of output molecules, while keeping the inputs robust to noise and the outputs at precise values. Moreover, arbitrarily complex circuit behaviors can be implemented with just a single type of molecular building block.", "date": "2018-01", "date_type": "published", "publication": "Proceedings of the National Academy of Sciences of the United States of America", "volume": "115", "number": "5", "publisher": "National Academy of Sciences", "pagerange": "903-908", "id_number": "CaltechAUTHORS:20180117-072812871", "issn": "0027-8424", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20180117-072812871", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "funders": { "items": [ { "agency": "NSF", "grant_number": "CCF-0832824" }, { "agency": "Burroughs Wellcome Fund", "grant_number": "1010684" }, { "agency": "NSF", "grant_number": "CCF-1351081" } ] }, "other_numbering_system": { "items": [ { "id": "etr-139", "name": "PARADISE" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "doi": "10.1073/pnas.1715926115", "pmcid": "PMC5798357", "primary_object": { "basename": "903.full.pdf", "url": "https://authors.library.caltech.edu/records/9wjw1-zhb03/files/903.full.pdf" }, "related_objects": [ { "basename": "pnas.1715926115.sapp.pdf", "url": "https://authors.library.caltech.edu/records/9wjw1-zhb03/files/pnas.1715926115.sapp.pdf" } ], "pub_year": "2018", "author_list": "Wilhelm, Daniel; Bruck, Jehoshua; et el." }, { "id": "https://authors.library.caltech.edu/records/28k7n-46f98", "eprint_id": 79070, "eprint_status": "archive", "datestamp": "2023-08-19 03:55:02", "lastmod": "2023-10-26 14:34:21", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Huang-Wentao", "name": { "family": "Huang", "given": "Wentao" }, "orcid": "0000-0003-0963-3624" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Generic Secure Repair for Distributed Storage", "ispublished": "unpub", "full_text_status": "public", "note": "Submitted - etr137.pdf
", "abstract": "This paper studies the problem of repairing secret sharing schemes, i.e., schemes that encode a message into n shares, assigned to n nodes, so that any n \u2212 r nodes can decode the message but any colluding z nodes cannot infer any information about the message. In the event of node failures so that shares held by the failed nodes are lost, the system needs to be repaired by\nreconstructing and reassigning the lost shares to the failed (or replacement) nodes. This can be achieved trivially by a trustworthy third-party that receives the shares of the available nodes, recompute and reassign the lost shares. The interesting question, studied in the paper, is how to repair without a trustworthy third-party. The main issue that arises is repair security: how to maintain the\nrequirement that any colluding z nodes, including the failed nodes, cannot learn any information about the message, during and after the repair process? We solve this secure repair problem from the perspective of secure multi-party computation. Specifically, we design generic repair schemes that can securely repair any (scalar or vector) linear secret sharing schemes. We prove a lower bound on the repair bandwidth of secure repair schemes and show that the proposed secure repair schemes achieve the optimal\nrepair bandwidth up to a small constant factor when\nn dominates z, or when the secret sharing scheme being repaired has optimal rate. We adopt a formal information-theoretic approach in our analysis and bounds. A main idea in our schemes is to allow a more flexible repair model than the straightforward one-round repair model implicitly assumed by existing secure regenerating codes. Particularly, the proposed secure repair schemes are simple and efficient two-round protocols.", "date": "2017-07-13", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20170713-092535943", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20170713-092535943", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "other_numbering_system": { "items": [ { "id": "ETR137", "name": "PARADISE" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "doi": "10.48550/arXiv.1706.00500", "primary_object": { "basename": "etr137.pdf", "url": "https://authors.library.caltech.edu/records/28k7n-46f98/files/etr137.pdf" }, "pub_year": "2017", "author_list": "Huang, Wentao and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/vq6gy-wh217", "eprint_id": 73557, "eprint_status": "archive", "datestamp": "2023-08-19 00:48:38", "lastmod": "2023-10-20 23:26:18", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Jain-Siddharth", "name": { "family": "Jain", "given": "Siddharth" }, "orcid": "0000-0002-9164-6119" }, { "id": "Farnoud-Farzad", "name": { "family": "Farnoud (Hassanzadeh)", "given": "Farzad" }, "orcid": "0000-0002-8684-4487" }, { "id": "Schwartz-Moshe", "name": { "family": "Schwartz", "given": "Moshe" }, "orcid": "0000-0002-1449-0026" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Noise and Uncertainty in String-Duplication Systems", "ispublished": "unpub", "full_text_status": "public", "note": "This work was supported in part by the NSF Expeditions in Computing Program (The Molecular Programming Project).\n\nSubmitted - etr134.pdf
", "abstract": "Duplication mutations play a critical role in the\ngeneration of biological sequences. Simultaneously, they\nhave a deleterious effect on data stored using in-vivo DNA data storage. While duplications have been studied both as a sequence-generation mechanism and in the context of error correction, for simplicity these studies have not taken into account the presence of other types of mutations. In this work, we consider the capacity of duplication mutations in the presence of point-mutation\nnoise, and so quantify the generation power of these mutations. We show that if the number of point mutations is vanishingly small compared to the number of duplication mutations of a constant length, the generation capacity of these mutations is zero. However, if the number of point mutations increases to a constant fraction of the number of duplications, then the capacity is nonzero. Lower and upper bounds for this capacity are also presented. Another problem that we study is concerned with the\nmismatch between code design and channel in data storage in the DNA of living organisms with respect to duplication mutations. In this context, we consider the uncertainty of such a mismatched coding scheme measured as the maximum number of input codewords that can lead to the same output.", "date": "2017-01-19", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20170119-133807104", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20170119-133807104", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "funders": { "items": [ { "agency": "NSF" } ] }, "other_numbering_system": { "items": [ { "id": "etr134", "name": "PARADISE" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr134.pdf", "url": "https://authors.library.caltech.edu/records/vq6gy-wh217/files/etr134.pdf" }, "pub_year": "2017", "author_list": "Jain, Siddharth; Farnoud (Hassanzadeh), Farzad; et el." }, { "id": "https://authors.library.caltech.edu/records/p1xt4-p6969", "eprint_id": 71814, "eprint_status": "archive", "datestamp": "2023-08-20 14:03:21", "lastmod": "2023-10-23 15:15:52", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Alon-Noga", "name": { "family": "Alon", "given": "Noga" }, "orcid": "0000-0003-1332-4883" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" }, { "id": "Farnoud-Farzad", "name": { "family": "Farnoud (Hassanzadeh)", "given": "Farzad" }, "orcid": "0000-0002-8684-4487" }, { "id": "Jain-Siddharth", "name": { "family": "Jain", "given": "Siddharth" }, "orcid": "0000-0002-9164-6119" } ] }, "title": "Duplication Distance to the Root for Binary Sequences", "ispublished": "unpub", "full_text_status": "public", "note": "This paper was presented in part at 2016 IEEE International Symposium on Information Theory in Barcelona, Spain. \n\nThis work was supported in part by the NSF Expeditions in Computing Program (The Molecular Programming Project), by a USA-Israeli BSF grant 2012/107, by an ISF grant 620/13, and by the Israeli I-Core program.\n\nSubmitted - etr133.pdf
", "abstract": "We study the tandem duplication distance between binary sequences and their roots. In other words, the quantity of interest is the number of tandem duplication operations of the form x = abc \u2192 y = abbc, where\nx and y are sequences and a, b, and c are their substrings, needed to generate a binary sequence of length\nn starting from a square-free sequence from the set\n{0, 1, 01, 10, 010, 101}. This problem is a restricted case of finding the duplication/deduplication\ndistance between two sequences, defined as the minimum number of duplication and deduplication\noperations required to transform one sequence to the other. We consider both exact and approximate tandem duplications. For exact duplication, denoting the maximum distance to the root of a sequence of length n by f(n), we prove that\nf(n) = \u03b8(n). For the case of approximate\nduplication, where a \u03b2-fraction of symbols may be duplicated incorrectly, we show that the\nmaximum distance has a sharp transition from linear in n to logarithmic at \u03b2 = 1/2. We also\nstudy the duplication distance to the root for sequences with a given root and for special classes of\nsequences, namely, the de Bruijn sequences, the Thue-Morse sequence, and the Fibbonaci words.\nThe problem is motivated by genomic tandem duplication mutations and the smallest number of\ntandem duplication events required to generate a given biological sequence.", "date": "2016-11-09", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20161108-134615672", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20161108-134615672", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "funders": { "items": [ { "agency": "NSF" }, { "agency": "Binational Science Foundation (USA-Israel)", "grant_number": "2012/107" }, { "agency": "Israel Science Foundation", "grant_number": "620/13" }, { "agency": "I-CORE Program of the Planning and Budgeting Committee" } ] }, "other_numbering_system": { "items": [ { "id": "etr133", "name": "PARADISE" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr133.pdf", "url": "https://authors.library.caltech.edu/records/p1xt4-p6969/files/etr133.pdf" }, "pub_year": "2016", "author_list": "Alon, Noga; Bruck, Jehoshua; et el." }, { "id": "https://authors.library.caltech.edu/records/fmjec-t7m90", "eprint_id": 63940, "eprint_status": "archive", "datestamp": "2023-08-20 09:42:31", "lastmod": "2023-10-17 18:30:14", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Jain-Siddharth", "name": { "family": "Jain", "given": "Siddharth" }, "orcid": "0000-0002-9164-6119" }, { "id": "Farnoud-Farzad", "name": { "family": "Farnoud (Hassanzadeh)", "given": "Farzad" }, "orcid": "0000-0002-8684-4487" }, { "id": "Schwartz-Moshe", "name": { "family": "Schwartz", "given": "Moshe" }, "orcid": "0000-0002-1449-0026" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Duplication-Correcting Codes for Data Storage in the DNA of Living Organisms", "ispublished": "unpub", "full_text_status": "public", "note": "This work was supported in part by the NSF Expeditions in Computing Program (The Molecular Programming Project).\n\nSubmitted - etr131.pdf
", "abstract": "The ability to store data in the DNA of a living\norganism has applications in a variety of areas including synthetic biology and watermarking of patented genetically-modified organisms. Data stored in this medium is subject to errors arising from various mutations, such as point mutations, indels, and tandem duplication, which need to be corrected to maintain data integrity. In this paper, we provide error-correcting codes for errors caused by tandem duplications, which create a copy of a block of the sequence and insert it in a tandem manner, i.e., next\nto the original. In particular, we present two families of codes for correcting errors due to tandem-duplications of a fixed length; the first family can correct any number of errors while the second corrects a bounded number of errors. We also study codes for correcting tandem duplications of length up to a given constant\nk, where we are primarily focused on the cases of k = 2, 3.", "date": "2016-01-26", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20160125-143414675", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20160125-143414675", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "funders": { "items": [ { "agency": "NSF" } ] }, "other_numbering_system": { "items": [ { "id": "etr131", "name": "PARADISE" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "doi": "10.1109/ISIT.2016.7541455", "primary_object": { "basename": "etr131.pdf", "url": "https://authors.library.caltech.edu/records/fmjec-t7m90/files/etr131.pdf" }, "pub_year": "2016", "author_list": "Jain, Siddharth; Farnoud (Hassanzadeh), Farzad; et el." }, { "id": "https://authors.library.caltech.edu/records/g8ntm-21346", "eprint_id": 63931, "eprint_status": "archive", "datestamp": "2023-08-20 09:59:28", "lastmod": "2023-10-17 18:29:26", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Huang-Wentao", "name": { "family": "Huang", "given": "Wentao" }, "orcid": "0000-0003-0963-3624" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Secure RAID Schemes for Distributed Storage", "ispublished": "unpub", "full_text_status": "public", "note": "Submitted - etr132.pdf
", "abstract": "We propose secure RAID, i.e., low-complexity schemes to store information in a distributed manner that is resilient to node failures and resistant to node eavesdropping. We generalize the concept of systematic encoding to secure RAID and show that systematic schemes have significant advantages in the efficiencies of encoding, decoding and random access. For the practical high rate regime, we construct three XOR-based systematic secure RAID schemes with optimal or almost optimal encoding and\ndecoding complexities, from the EVENODD codes and B codes, which are array codes widely used in the RAID architecture. The schemes can tolerate up to two node failures and two eavesdropping nodes. For more general parameters we construct systematic secure RAID schemes from Reed-Solomon codes, and show that they are significantly more efficient than Shamir's secret sharing scheme. Our results suggest that building \"keyless\", information-theoretic security into the RAID architecture is practical.", "date": "2016-01-25", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20160125-120110556", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20160125-120110556", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "other_numbering_system": { "items": [ { "id": "etr132", "name": "PARADISE" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "doi": "10.1109/ISIT.2016.7541529", "primary_object": { "basename": "etr132.pdf", "url": "https://authors.library.caltech.edu/records/g8ntm-21346/files/etr132.pdf" }, "pub_year": "2016", "author_list": "Huang, Wentao and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/0518b-hky47", "eprint_id": 57900, "eprint_status": "archive", "datestamp": "2023-08-20 06:01:37", "lastmod": "2023-10-23 17:53:08", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Huang-Wentao", "name": { "family": "Huang", "given": "Wentao" }, "orcid": "0000-0003-0963-3624" }, { "id": "Langberg-M", "name": { "family": "Langberg", "given": "Michael" }, "orcid": "0000-0002-7470-0718" }, { "id": "Kliewer-J", "name": { "family": "Kliewer", "given": "Joerg" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Communication Efficient Secret Sharing", "ispublished": "unpub", "full_text_status": "public", "note": "Submitted - etr130.pdf
", "abstract": "A secret sharing scheme is a method to store information securely and reliably. Particularly, in the threshold secret sharing scheme (due to Shamir), a secret is divided\ninto shares, encoded and distributed to parties, such that any large enough collection of parties can decode the secret, and a smaller (then threshold) set of parties cannot\ncollude to deduce any information about the secret. While Shamir's scheme was studied for more than 35 years, the question of minimizing its communication bandwidth was\nnot considered. Specifically, assume that a user (or a collection of parties) wishes to decode the secret by receiving information from a set of parties; the question we\nstudy is how to minimize the total amount of communication between the user and the parties. We prove a tight lower bound on the amount of communication necessary for\ndecoding, and construct secret sharing schemes achieving the bound. The key idea for achieving optimal communication bandwidth is to let the user receive information from\nmore than the necessary number of parties. In contrast, the current paradigm in secret sharing schemes is to decode from a minimum set of parties. Hence, existing secret\nsharing schemes are not optimal in terms of communication bandwidth. In addition, we consider secure distributed storage where our proposed communication efficient secret\nsharing schemes improve disk access complexity during decoding.", "date": "2015-05-29", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20150529-105023455", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20150529-105023455", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "other_numbering_system": { "items": [ { "id": "ETR130", "name": "Paradise" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "doi": "10.1109/TIT.2016.2616144", "primary_object": { "basename": "etr130.pdf", "url": "https://authors.library.caltech.edu/records/0518b-hky47/files/etr130.pdf" }, "pub_year": "2015", "author_list": "Huang, Wentao; Langberg, Michael; et el." }, { "id": "https://authors.library.caltech.edu/records/vyjrj-amv90", "eprint_id": 54604, "eprint_status": "archive", "datestamp": "2023-08-20 04:21:37", "lastmod": "2023-10-20 23:11:05", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Farnoud-Farzad", "name": { "family": "Farnoud (Hassanzadeh)", "given": "Farzad" }, "orcid": "0000-0002-8684-4487" }, { "id": "Schwartz-Moshe", "name": { "family": "Schwartz", "given": "Moshe" }, "orcid": "0000-0002-1449-0026" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "A Stochastic Model for Genomic Interspersed Duplication", "ispublished": "unpub", "full_text_status": "public", "note": "Submitted - etr129.pdf
", "abstract": "Mutation processes such as point mutation, insertion,\ndeletion, and duplication (including tandem and interspersed\nduplication) have an important role in evolution, as\nthey lead to genomic diversity, and thus to phenotypic variation. In this work, we study the expressive power of interspersed duplication, i.e., its ability to generate diversity, via a simple but fundamental stochastic model, where the length and the location of the subsequence that is duplicated and the point of insertion of the copy are chosen randomly. In contrast to combinatorial models, where the goal is to determine the set of possible outcomes regardless of their likelihood, in stochastic\nsystems, we investigate the properties of the set of high-probability sequences. In particular we provide results regarding the asymptotic behavior of frequencies of symbols and short words in a sequence evolving through interspersed duplication. The study of such a systems is an important step towards the design and analysis of more realistic and sophisticated models of genomic mutation processes.", "date": "2015-02-10", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20150209-161532302", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20150209-161532302", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "other_numbering_system": { "items": [ { "id": "ETR129", "name": "Paradise" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr129.pdf", "url": "https://authors.library.caltech.edu/records/vyjrj-amv90/files/etr129.pdf" }, "pub_year": "2015", "author_list": "Farnoud (Hassanzadeh), Farzad; Schwartz, Moshe; et el." }, { "id": "https://authors.library.caltech.edu/records/asa2n-zzv53", "eprint_id": 54593, "eprint_status": "archive", "datestamp": "2023-08-20 04:21:28", "lastmod": "2023-10-20 23:10:59", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Jain-Siddharth", "name": { "family": "Jain", "given": "Siddharth" }, "orcid": "0000-0002-9164-6119" }, { "id": "Farnoud-Farzad", "name": { "family": "Farnoud (Hassanzadeh)", "given": "Farzad" }, "orcid": "0000-0002-8684-4487" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Capacity and Expressiveness of Genomic Tandem Duplication", "ispublished": "unpub", "full_text_status": "public", "note": "Submitted - etr127.pdf
", "abstract": "The majority of the human genome consists of repeated sequences. An important type of repeats common in the human genome are tandem repeats, where identical copies appear next to each other. For example, in the sequence AGTCTGTGC, TGTG is a tandem repeat, namely, it was generated from AGTCTGC by tandem duplication of length 2. In this work, we investigate the possibility of generating a large number of sequences from a small initial string (called\nthe seed) by tandem duplication of length bounded by a constant. Our results include exact capacity values for certain tandem duplication string systems with alphabet sizes 2; 3; and 4. In addition, motivated by the role of DNA sequences in expressing proteins via RNA and the genetic code, we define the notion of the expressiveness of a tandem duplication system, as the feasibility of\nexpressing arbitrary substrings. We then completely characterize the expressiveness of tandem duplication systems for general alphabet sizes and duplication lengths. Noticing that a system with capacity = 1 is expressive, we prove that for an alphabet size \u2265 4, the capacity is strictly smaller than 1, independent of\nthe seed and the duplication lengths. The proof of this limit on the capacity (note that the genomic alphabet size is 4), is related to an interesting result by Axel Thue from 1906 which states that there exist arbitrary length sequences with no tandem repeats (square-free) for alphabet size \u2265 3. Finally, our results illustrate\nthat duplication lengths play a more significant role than the seed in generating a large number of sequences for these systems.", "date": "2015-02-10", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20150209-155348874", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20150209-155348874", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "other_numbering_system": { "items": [ { "id": "ETR127", "name": "Paradise" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "doi": "10.48550/arXiv.1509.06029", "primary_object": { "basename": "etr127.pdf", "url": "https://authors.library.caltech.edu/records/asa2n-zzv53/files/etr127.pdf" }, "pub_year": "2015", "author_list": "Jain, Siddharth; Farnoud (Hassanzadeh), Farzad; et el." }, { "id": "https://authors.library.caltech.edu/records/7kq5n-d3534", "eprint_id": 54602, "eprint_status": "archive", "datestamp": "2023-08-20 04:21:33", "lastmod": "2023-10-20 19:09:21", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "En-Gad-E", "name": { "family": "En Gad", "given": "Eyal" } }, { "id": "Huang-Wentao", "name": { "family": "Huang", "given": "Wentao" }, "orcid": "0000-0003-0963-3624" }, { "id": "Li-Yue", "name": { "family": "Li", "given": "Yue" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Rewriting Flash Memories by Message Passing", "ispublished": "unpub", "full_text_status": "public", "note": "Submitted - etr128.pdf
", "abstract": "This paper constructs WOM codes that combine\nrewriting and error correction for mitigating the reliability and the endurance problems in flash memory.We consider a rewriting model that is of practical interest to flash applications where only the second write uses WOM codes. Our WOM code construction is based on binary erasure quantization with LDGM codes, where the rewriting uses message passing and has potential to share the\nefficient hardware implementations with LDPC codes in practice. We show that the coding scheme achieves the capacity of the rewriting model. Extensive simulations show that the rewriting performance of our scheme compares favorably with that of polar WOM code in the rate region where high rewriting success probability is desired. We further augment our coding schemes with error correction capability. By drawing a connection to the\nconjugate code pairs studied in the context of quantum error\ncorrection, we develop a general framework for constructing\nerror-correction WOM codes. Under this framework, we give\nan explicit construction of WOM codes whose codewords are\ncontained in BCH codes.", "date": "2015-02-10", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20150209-161244506", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20150209-161244506", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "other_numbering_system": { "items": [ { "id": "ETR128", "name": "Paradise" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "doi": "10.48550/arXiv.1502.00189", "primary_object": { "basename": "etr128.pdf", "url": "https://authors.library.caltech.edu/records/7kq5n-d3534/files/etr128.pdf" }, "pub_year": "2015", "author_list": "En Gad, Eyal; Huang, Wentao; et el." }, { "id": "https://authors.library.caltech.edu/records/t5pap-5z628", "eprint_id": 54481, "eprint_status": "archive", "datestamp": "2023-08-20 03:11:06", "lastmod": "2023-10-20 23:17:15", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "En-Gad-E", "name": { "family": "En Gad", "given": "Eyal" } }, { "id": "Li-Yue", "name": { "family": "Li", "given": "Yue" } }, { "id": "Kliewer-J", "name": { "family": "Kliewer", "given": "Joerg" } }, { "id": "Langberg-M", "name": { "family": "Langberg", "given": "Michael" }, "orcid": "0000-0002-7470-0718" }, { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Asymmetric Error Correction and Flash-Memory Rewriting using Polar Codes", "ispublished": "unpub", "full_text_status": "public", "note": "The material in this paper was presented in part at the IEEE Int. Symp. on Inform. Theory (ISIT), Honolulu, HI, USA, July 2014 [8]. This work was supported in part by Intellectual Ventures, NSF grants CIF-1218005, CCF-1439465, CCF-1440001 and CCF-1320785, NSF CAREER Award CCF-0747415 and the US-Israel Binational Science Foundation (BSF) under Grant No. 2010075.\n\nSubmitted - etr124.pdf
", "abstract": "We propose efficient coding schemes for two communication settings: 1. asymmetric channels, and 2. channels\nwith an informed encoder. These settings are important in non-volatile memories, as well as optical and broadcast\ncommunication. The schemes are based on non-linear polar codes, and they build on and improve recent work\non these settings. In asymmetric channels, we tackle the exponential storage requirement of previously known\nschemes, that resulted from the use of large Boolean functions. We propose an improved scheme, that achieves the\ncapacity of asymmetric channels with polynomial computational complexity and storage requirement.\n\nThe proposed non-linear scheme is then generalized to the setting of channel coding with an informed encoder,\nusing a multicoding technique. We consider specific instances of the scheme for flash memories, that incorporate\nerror-correction capabilities together with rewriting. Since the considered codes are non-linear, they eliminate\nthe requirement of previously known schemes (called polar write-once-memory codes) for shared randomness\nbetween the encoder and the decoder. Finally, we mention that the multicoding scheme is also useful for broadcast\ncommunication in Marton's region, improving upon previous schemes for this setting.", "date": "2015-02-06", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20150206-113520153", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20150206-113520153", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "funders": { "items": [ { "agency": "Intellectual Ventures" }, { "agency": "NSF", "grant_number": "CIF-1218005" }, { "agency": "NSF", "grant_number": "CCF-1439465" }, { "agency": "NSF", "grant_number": "CCF-1320785" }, { "agency": "NSF", "grant_number": "CCF-0747415" }, { "agency": "Binational Science Foundation (USA-Israel)", "grant_number": "2010075" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "doi": "10.1109/TIT.2016.2539967", "primary_object": { "basename": "etr124.pdf", "url": "https://authors.library.caltech.edu/records/t5pap-5z628/files/etr124.pdf" }, "pub_year": "2015", "author_list": "En Gad, Eyal; Li, Yue; et el." }, { "id": "https://authors.library.caltech.edu/records/zcv5z-eg591", "eprint_id": 54307, "eprint_status": "archive", "datestamp": "2023-08-20 03:26:32", "lastmod": "2023-10-20 15:48:07", "type": "article", "metadata_visibility": "show", "creators": { "items": [ { "id": "Zhou-Hongchao", "name": { "family": "Zhou", "given": "Hongchao" } }, { "id": "Schwartz-Moshe", "name": { "family": "Schwartz", "given": "Moshe" }, "orcid": "0000-0002-1449-0026" }, { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Systematic Error-Correcting Codes for Rank Modulation", "ispublished": "pub", "full_text_status": "public", "keywords": "Flash memory, rank modulation, error correcting codes, permutations, metric embeddings, Kendall's \u03c4 -metric, \u2113\u221e-metric, systematic codes", "note": "\u00a9 2014 IEEE. \n\nManuscript received October 25, 2013; revised August 14, 2014; accepted October 12, 2014. Date of publication October 28, 2014; date of current version December 22, 2014. \n\nThis work was supported in part by the U.S.- Israel Binational Science Foundation under Grant 2010075, in part by the National Science Foundation (NSF) under Grant CCF-1218005, in part by the NSF CAREER under Award CCF-0747415, and in part by the NSF under Grant CCF-1217944. This paper was presented at the 2012 IEEE International Symposium on Information Theory.\n\nSubmitted - 1310.6817.pdf
", "abstract": "The rank-modulation scheme has been recently proposed for efficiently storing data in nonvolatile memories. In this paper, we explore [n, k, d] systematic error-correcting codes for rank modulation. Such codes have length n, k information symbols, and minimum distance d. Systematic codes have the benefits of enabling efficient information retrieval in conjunction with memory-scrubbing schemes. We study systematic codes for rank modulation under Kendall's T-metric as well as under the \u2113\u221e-metric. In Kendall's T-metric, we present [k + 2, k, 3] systematic codes for correcting a single error, which have optimal rates, unless systematic perfect codes exist. We also study the design of multierror-correcting codes, and provide a construction of [k + t + 1, k, 2t + 1] systematic codes, for large-enough k. We use nonconstructive arguments to show that for rank modulation, systematic codes achieve the same capacity as general error-correcting codes. Finally, in the \u2113\u221e-metric, we construct two [n, k, d] systematic multierror-correcting codes, the first for the case of d = 0(1) and the second for d = \u0398(n). In the latter case, the codes have the same asymptotic rate as the best codes currently known in this metric.", "date": "2014-10-28", "date_type": "published", "publication": "IEEE Transactions on Information Theory", "volume": "61", "number": "1", "publisher": "IEEE", "pagerange": "17-32", "id_number": "CaltechAUTHORS:20150202-150301749", "issn": "0018-9448", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20150202-150301749", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "funders": { "items": [ { "agency": "Binational Science Foundation (USA-Israel)", "grant_number": "2010075" }, { "agency": "NSF", "grant_number": "CCF-1218005" }, { "agency": "NSF", "grant_number": "CCF-0747415" }, { "agency": "NSF", "grant_number": "CCF-1217944" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "doi": "10.1109/TIT.2014.2365499", "primary_object": { "basename": "1310.6817.pdf", "url": "https://authors.library.caltech.edu/records/zcv5z-eg591/files/1310.6817.pdf" }, "pub_year": "2014", "author_list": "Zhou, Hongchao; Schwartz, Moshe; et el." }, { "id": "https://authors.library.caltech.edu/records/xw27t-p9b59", "eprint_id": 43524, "eprint_status": "archive", "datestamp": "2023-08-19 22:51:11", "lastmod": "2023-10-25 23:37:42", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Farnoud-Farzad", "name": { "family": "Farnoud (Hassanzadeh)", "given": "Farzad" }, "orcid": "0000-0002-8684-4487" }, { "id": "Schwartz-Moshe", "name": { "family": "Schwartz", "given": "Moshe" }, "orcid": "0000-0002-1449-0026" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Rate-Distortion for Ranking with Incomplete Information", "ispublished": "unpub", "full_text_status": "public", "note": "Accepted Version - etr125.pdf
", "abstract": "We study the rate-distortion relationship in the set\nof permutations endowed with the Kendall t-metric and the\nChebyshev metric. Our study is motivated by the application of permutation rate-distortion to the average-case and worst-case analysis of algorithms for ranking with incomplete information and approximate sorting algorithms. For the Kendall t-metric we provide bounds for small, medium, and large distortion regimes, while for the Chebyshev metric we present bounds that are valid for all distortions and are especially accurate for small\ndistortions. In addition, for the Chebyshev metric, we provide a construction for covering codes.", "date": "2014-01-28", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20140127-104737329", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20140127-104737329", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "other_numbering_system": { "items": [ { "id": "ETR125", "name": "Paradise" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "doi": "10.48550/arXiv.1401.3093", "primary_object": { "basename": "etr125.pdf", "url": "https://authors.library.caltech.edu/records/xw27t-p9b59/files/etr125.pdf" }, "pub_year": "2014", "author_list": "Farnoud (Hassanzadeh), Farzad; Schwartz, Moshe; et el." }, { "id": "https://authors.library.caltech.edu/records/gnct0-whj77", "eprint_id": 43526, "eprint_status": "archive", "datestamp": "2023-08-19 22:51:16", "lastmod": "2023-10-25 23:37:44", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Farnoud-Farzad", "name": { "family": "Farnoud (Hassanzadeh)", "given": "Farzad" }, "orcid": "0000-0002-8684-4487" }, { "id": "Schwartz-Moshe", "name": { "family": "Schwartz", "given": "Moshe" }, "orcid": "0000-0002-1449-0026" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "The Capacity of String-Replication Systems", "ispublished": "unpub", "full_text_status": "public", "note": "This work was supported in part by the NSF Expeditions in Computing Program (The Molecular Programming Project).\n\nAccepted Version - etr126.pdf
", "abstract": "It is known that the majority of the human genome\nconsists of repeated sequences. Furthermore, it is believed that a significant part of the rest of the genome also originated from repeated sequences and has mutated to its current form. In this paper, we investigate the possibility of constructing an exponentially large number of sequences from a short initial sequence and simple replication rules, including those resembling genomic replication processes. In other words, our goal is to find out the capacity, or the expressive power, of these string-replication\nsystems. Our results include exact capacities, and\nbounds on the capacities, of four fundamental string-replication systems.", "date": "2014-01-28", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20140127-105959677", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20140127-105959677", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "funders": { "items": [ { "agency": "NSF" } ] }, "other_numbering_system": { "items": [ { "id": "ETR126", "name": "Paradise" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "doi": "10.48550/arXiv.1401.4634", "primary_object": { "basename": "etr126.pdf", "url": "https://authors.library.caltech.edu/records/gnct0-whj77/files/etr126.pdf" }, "pub_year": "2014", "author_list": "Farnoud (Hassanzadeh), Farzad; Schwartz, Moshe; et el." }, { "id": "https://authors.library.caltech.edu/records/81c1h-c4n08", "eprint_id": 36945, "eprint_status": "archive", "datestamp": "2023-08-19 14:10:20", "lastmod": "2023-10-23 15:58:23", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Farnoud-Farzad", "name": { "family": "Farnoud (Hassanzadeh)", "given": "Farzad" }, "orcid": "0000-0002-8684-4487" }, { "id": "Yaakobi-E", "name": { "family": "Yaakobi", "given": "Eitan" }, "orcid": "0000-0002-9851-5234" }, { "id": "Touri-B", "name": { "family": "Touri", "given": "Behrouz" } }, { "id": "Milenkovic-O", "name": { "family": "Milenkovic", "given": "Olgica" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Building Consensus via Iterative Voting", "ispublished": "unpub", "full_text_status": "public", "note": "The authors are grateful to Angelia Nedich for useful discussions. \n\nThe work was partially supported by NSF grants CCF 0939370, CCF 0644427, ECCS-0801795 and BSF grant 2010075.\n\nSubmitted - etr121.pdf
", "abstract": "In networked systems comprised of many agents, it is often required to reach a common operating point of all agents, termed the network consensus. We consider two iterative methods for reaching a ranking (ordering) consensus over a voter network, where the initial preference of every voter is of the form of a full ordering of candidates. The voters are allowed, one at a time and based on some random scheme, to change their vote to bring them \"closer\" to the opinions of selected subsets of peers. The first consensus method is based on changing votes one adjacent swap at a time; the second method is based on changing a vote via averaging with the\nvotes of peers, potentially leading to many adjacent swaps at a time vote. For the first model, we characterize convergence points and conditions for convergence. For the second model, we prove convergence to a global ranking and derive the rate of convergence to this consensus.", "date": "2013-02-15", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20130215-093909657", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20130215-093909657", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "funders": { "items": [ { "agency": "NSF", "grant_number": "CCF-0939370" }, { "agency": "NSF", "grant_number": "CCF-0644427" }, { "agency": "NSF", "grant_number": "ECCS-0801795" }, { "agency": "Binational Science Foundation (USA-Israel)", "grant_number": "2010075" } ] }, "other_numbering_system": { "items": [ { "id": "ETR121", "name": "Paradise" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr121.pdf", "url": "https://authors.library.caltech.edu/records/81c1h-c4n08/files/etr121.pdf" }, "pub_year": "2013", "author_list": "Farnoud (Hassanzadeh), Farzad; Yaakobi, Eitan; et el." }, { "id": "https://authors.library.caltech.edu/records/ft4vp-ka042", "eprint_id": 36946, "eprint_status": "archive", "datestamp": "2023-08-19 14:10:24", "lastmod": "2023-10-23 15:58:25", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Buzaglo-S", "name": { "family": "Buzaglo", "given": "Sarit" } }, { "id": "Yaakobi-E", "name": { "family": "Yaakobi", "given": "Eitan" }, "orcid": "0000-0002-9851-5234" }, { "id": "Etzion-T", "name": { "family": "Etzion", "given": "Tuvi" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Error-Correcting Codes for Multipermutations", "ispublished": "unpub", "full_text_status": "public", "note": "The work of Sarit Buzaglo and Tuvi Etzion was supported in\npart by the Israel Science Foundation (ISF), Jerusalem, Israel,\nunder Grant No. 10/12. The authors would like to thank Alexander\nVardy and Michael Langberg for bringing reference [9] to\ntheir knowledge.", "abstract": "THIS PAPER IS ELIGIBLE FOR THE STUDENT\nPAPER AWARD. Multipermutations appear in various applications\nin information theory. New applications such as rank\nmodulation for flash memories and voting have suggested the need\nto consider error-correcting codes for multipermutations. The construction\nof codes is challenging when permutations are considered\nand it becomes even a harder problem for multipermutations. In\nthis paper we discuss the general problem of error-correcting codes\nfor multipermutations. We present some tight bounds on the size of\nerror-correcting codes for several families of multipermutations.\nWe find the capacity of the channels of multipermutations and\ncharacterize families of perfect codes in this metric which we\nbelieve are the only such perfect codes.", "date": "2013-02-15", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20130215-094523026", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20130215-094523026", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "funders": { "items": [ { "agency": "Israel Science Foundation", "grant_number": "10/12" } ] }, "other_numbering_system": { "items": [ { "id": "ETR122", "name": "Paradise" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr122.pdf", "url": "https://authors.library.caltech.edu/records/ft4vp-ka042/files/etr122.pdf" }, "pub_year": "2013", "author_list": "Buzaglo, Sarit; Yaakobi, Eitan; et el." }, { "id": "https://authors.library.caltech.edu/records/8g08j-vwq41", "eprint_id": 36942, "eprint_status": "archive", "datestamp": "2023-08-19 14:10:11", "lastmod": "2023-10-23 15:58:14", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Yaakobi-E", "name": { "family": "Yaakobi", "given": "Eitan" }, "orcid": "0000-0002-9851-5234" }, { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "In-Memory Computing of Akers Logic Array", "ispublished": "unpub", "full_text_status": "public", "abstract": "This work studies memories from a different perspective,\nwhile the goal is to explore the concept of in-memory\ncomputing. Our point of departure is an old study of logic arrays\nby Akers in 1972. We demonstrate how these arrays can\nsimultaneously store information and perform logic operations.\n\nWe first extend the structure of these arrays for non-binary\nalphabets. We then show how a special structure of these arrays\ncan both store elements and output a sorted version of them. We\nalso study other examples of the in-memory computing concept.\nIn this setup, it is shown how information can be stored and\ncomputed with, and the array can tolerate or detect errors in\nthe stored data.", "date": "2013-02-15", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20130215-092157295", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20130215-092157295", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "other_numbering_system": { "items": [ { "id": "ETR119", "name": "Paradise" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr119.pdf", "url": "https://authors.library.caltech.edu/records/8g08j-vwq41/files/etr119.pdf" }, "pub_year": "2013", "author_list": "Yaakobi, Eitan; Jiang, Anxiao (Andrew); et el." }, { "id": "https://authors.library.caltech.edu/records/ebd4t-esq24", "eprint_id": 36943, "eprint_status": "archive", "datestamp": "2023-08-19 14:10:15", "lastmod": "2023-10-23 15:58:16", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Yaakobi-E", "name": { "family": "Yaakobi", "given": "Eitan" }, "orcid": "0000-0002-9851-5234" }, { "id": "Langberg-M", "name": { "family": "Langberg", "given": "Michael" }, "orcid": "0000-0002-7470-0718" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Information-Theoretic Study of Voting Systems", "ispublished": "unpub", "full_text_status": "public", "abstract": "The typical paradigm in voting theory involves n\nvoters and m candidates. Every voter ranks the candidates resulting\nin a permutation of the m candidates. A key problem is\nto derive the aggregate result of the voting. A popular method\nfor vote aggregation is based on the Condorcet criterion. The\nCondorcet winner is the candidate who wins every other candidate\nby pairwise majority. However, the main disadvantage of\nthis approach, known as the Condorcet paradox, is that such a\nwinner does not necessarily exist since this criterion does not admit\ntransitivity. This paradox is mathematically likely (if voters\nassign rankings uniformly at random, then with probability approaching\none with the number of candidates, there will not be\na Condorcet winner), however, in real life scenarios such as elections,\nit is not likely to encounter the Condorcet paradox. In this\npaper we attempt to improve our intuition regarding the gap between\nthe mathematics and reality of voting systems. We study a\nspecial case where there is global intransitivity between all candidates.\nWe introduce tools from information theory and derive\nan entropy-based characterization of global intransitivity. In addition,\nwe tighten this characterization by assuming that votes\ntend to be similar; in particular they can be modeled as permutations\nthat are confined to a sphere defined by the Kendalls \u03c4\ndistance.", "date": "2013-02-15", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20130215-092855327", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20130215-092855327", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "funders": { "items": [ { "agency": "NSF", "grant_number": "ECCS-0801795" }, { "agency": "Binational Science Foundation (BSF)", "grant_number": "2010075" } ] }, "other_numbering_system": { "items": [ { "id": "ETR120", "name": "Paradise" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr120.pdf", "url": "https://authors.library.caltech.edu/records/ebd4t-esq24/files/etr120.pdf" }, "pub_year": "2013", "author_list": "Yaakobi, Eitan; Langberg, Michael; et el." }, { "id": "https://authors.library.caltech.edu/records/7ct46-a3j12", "eprint_id": 36634, "eprint_status": "archive", "datestamp": "2023-08-19 14:08:41", "lastmod": "2023-10-20 23:25:50", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Wang-Zhiying", "name": { "family": "Wang", "given": "Zhiying" } }, { "id": "Shaked-O", "name": { "family": "Shaked", "given": "Omer" } }, { "id": "Cassuto-Y", "name": { "family": "Cassuto", "given": "Yuval" }, "orcid": "0000-0001-6369-6699" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Codes for Network Switches", "ispublished": "unpub", "full_text_status": "public", "abstract": "A network switch routes data packets between its\nmultiple input and output ports. Packets from input ports are\nstored upon arrival in a switch fabric comprising multiple\nmemory banks. This can result in memory contention when\ndistinct output ports request packets from the same memory\nbank, resulting in a degraded switching bandwidth. To solve this\nproblem, we propose to add redundant memory banks for storing\nthe incoming packets. The problem we address is how to minimize\nthe number of redundant memory banks given some guaranteed\ncontention resolution capability. We present constructions of\nnew switch memory architectures based on different coding\ntechniques. The codes allow decreasing the redundancy by 1/2\nor 2/3, depending on the request specifications, compared to\nnon-coding solutions.", "date": "2013-01-30", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20130128-153803180", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20130128-153803180", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr117.pdf", "url": "https://authors.library.caltech.edu/records/7ct46-a3j12/files/etr117.pdf" }, "pub_year": "2013", "author_list": "Wang, Zhiying; Shaked, Omer; et el." }, { "id": "https://authors.library.caltech.edu/records/h9m1f-ak728", "eprint_id": 36632, "eprint_status": "archive", "datestamp": "2023-08-19 14:08:37", "lastmod": "2023-10-20 23:25:21", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "En-Gad-E", "name": { "family": "En Gad", "given": "Eyal" } }, { "id": "Yaakobi-E", "name": { "family": "Yaakobi", "given": "Eitan" }, "orcid": "0000-0002-9851-5234" }, { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Rank-Modulation Rewriting Codes for Flash Memories", "ispublished": "unpub", "full_text_status": "public", "note": "This work was partially supported by the NSF grants ECCS-\n0801795 and CCF-1217944, NSF CAREER Award CCF-\n0747415, BSF grant 2010075 and a grant from Intellectual\nVentures.", "abstract": "Current flash memory technology is focused on\ncost minimization of the stored capacity. However, the resulting\napproach supports a relatively small number of write-erase\ncycles. This technology is effective for consumer devices (smartphones\nand cameras) where the number of write-erase cycles is\nsmall, however, it is not economical for enterprise storage systems\nthat require a large number of lifetime writes.\n\nOur proposed approach for alleviating this problem consists of\nthe efficient integration of two key ideas: (i) improving reliability\nand endurance by representing the information using relative\nvalues via the rank modulation scheme and (ii) increasing the\noverall (lifetime) capacity of the flash device via rewriting codes,\nnamely, performing multiple writes per cell before erasure.\n\nWe propose a new scheme that combines rank-modulation\nwith rewriting. The key benefits of the new scheme include: (i)\nthe ability to store close to 2 bits per cell on each write, and\nrewrite the memory close to q times, where q is the number\nof levels in each cell, and (ii) efficient encoding and decoding\nalgorithms that use the recently proposed polar WOM codes.", "date": "2013-01-30", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20130128-144020108", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20130128-144020108", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "funders": { "items": [ { "agency": "NSF", "grant_number": "ECCS-0801795" }, { "agency": "NSF", "grant_number": "CCF-1217944" }, { "agency": "NSF", "grant_number": "CCF-0747415" }, { "agency": "BSF", "grant_number": "2010075" }, { "agency": "Intellectual Venttures" } ] }, "other_numbering_system": { "items": [ { "id": "ETR117", "name": "Paradise" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr117.pdf", "url": "https://authors.library.caltech.edu/records/h9m1f-ak728/files/etr117.pdf" }, "pub_year": "2013", "author_list": "En Gad, Eyal; Yaakobi, Eitan; et el." }, { "id": "https://authors.library.caltech.edu/records/447km-4es02", "eprint_id": 36948, "eprint_status": "archive", "datestamp": "2023-08-19 14:10:29", "lastmod": "2023-10-23 15:58:28", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Yaakobi-E", "name": { "family": "Yaakobi", "given": "Eitan" }, "orcid": "0000-0002-9851-5234" }, { "id": "Schwartz-Moshe", "name": { "family": "Schwartz", "given": "Moshe" }, "orcid": "0000-0002-1449-0026" }, { "id": "Langberg-M", "name": { "family": "Langberg", "given": "Michael" }, "orcid": "0000-0002-7470-0718" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Sequence Reconstruction for Grassmann Graphs and Permutations", "ispublished": "unpub", "full_text_status": "public", "note": "This work was supported in part by an NSF grant ECCS-0801795 and a\nBSF grant 2010075.", "abstract": "The sequence-reconstruction problem was first proposed\nby Levenshtein in 2001. This problem studies the model\nwhere the same word is transmitted over multiple channels. If\nthe transmitted word belongs to some code of minimum distance\nd and there are at most r errors in every channel, then the minimum\nnumber of channels that guarantees a successful decoder\n(under the assumption that all channel outputs are distinct) has\nto be greater than the largest intersection of two balls of radius\nr and with distance at least d between their centers.\n\nThis paper studies the combinatorial problem of computing\nthe largest intersection of two balls for two cases. In the first\npart we solve this problem in the Grassmann graph for all values\nof d and r. In the second part we derive similar results for\npermutations under Kendall's t-metric for some special cases of\nd and r.", "date": "2013-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20130215-095250632", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20130215-095250632", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "funders": { "items": [ { "agency": "NSF", "grant_number": "ECCS-0801795" }, { "agency": "Binational Science Foundation (BSF)", "grant_number": "2010075" } ] }, "other_numbering_system": { "items": [ { "id": "ETR123", "name": "Paradise" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr123.pdf", "url": "https://authors.library.caltech.edu/records/447km-4es02/files/etr123.pdf" }, "pub_year": "2013", "author_list": "Yaakobi, Eitan; Schwartz, Moshe; et el." }, { "id": "https://authors.library.caltech.edu/records/xt2bt-jdt16", "eprint_id": 31923, "eprint_status": "archive", "datestamp": "2023-08-19 11:23:33", "lastmod": "2023-10-17 21:42:17", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Wang-Zhiying", "name": { "family": "Wang", "given": "Zhiying" } }, { "id": "Tamo-I", "name": { "family": "Tamo", "given": "Itzhak" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Long MDS Codes for Optimal Repair Bandwidth", "ispublished": "unpub", "full_text_status": "public", "note": "Submitted - etr116.pdf
", "abstract": "MDS codes are erasure-correcting codes that can\ncorrect the maximum number of erasures given the number of\nredundancy or parity symbols. If an MDS code has r parities\nand no more than r erasures occur, then by transmitting all\nthe remaining data in the code one can recover the original\ninformation. However, it was shown that in order to recover a\nsingle symbol erasure, only a fraction of 1/r of the information\nneeds to be transmitted. This fraction is called the repair\nbandwidth (fraction). Explicit code constructions were given in\nprevious works. If we view each symbol in the code as a vector\nor a column, then the code forms a 2D array and such codes\nare especially widely used in storage systems. In this paper, we\nask the following question: given the length of the column l, can\nwe construct high-rate MDS array codes with optimal repair\nbandwidth of 1/r, whose code length is as long as possible? In\nthis paper, we give code constructions such that the code length\nis (r + 1)log_r l.", "date": "2012-06-18", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20120616-221646611", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20120616-221646611", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "other_numbering_system": { "items": [ { "id": "ETR116", "name": "Paradise" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr116.pdf", "url": "https://authors.library.caltech.edu/records/xt2bt-jdt16/files/etr116.pdf" }, "pub_year": "2012", "author_list": "Wang, Zhiying; Tamo, Itzhak; et el." }, { "id": "https://authors.library.caltech.edu/records/gxf0c-h9x26", "eprint_id": 31507, "eprint_status": "archive", "datestamp": "2023-08-19 11:03:23", "lastmod": "2023-10-17 16:38:27", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "En-Gad-E", "name": { "family": "En Gad", "given": "Eyal" } }, { "id": "Jiang-Anxiao-Andrew", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Trade-offs between Instantaneous and Total Capacity in Multi-Cell Flash Memories", "ispublished": "unpub", "full_text_status": "public", "note": "This work was partially supported by an NSF grant ECCS-\n0801795 and a BSF grant 2010075. The author would like\nto acknowledge that Qing Li from Texas A&M University\nderived Lemmas 1 and 2 independently.\n\nSubmitted - etr115.pdf
", "abstract": "The limited endurance of flash memories is a major\ndesign concern for enterprise storage systems. We propose a\nmethod to increase it by using relative (as opposed to fixed)\ncell levels and by representing the information with Write\nAsymmetric Memory (WAM) codes. Overall, our new method\nenables faster writes, improved reliability as well as improved\nendurance by allowing multiple writes between block erasures.\nWe study the capacity of the new WAM codes with relative levels,\nwhere the information is represented by multiset permutations\ninduced by the charge levels, and show that it achieves the\ncapacity of any other WAM codes with the same number of\nwrites. Specifically, we prove that it has the potential to double\nthe total capacity of the memory. Since capacity can be achieved\nonly with cells that have a large number of levels, we propose a\nnew architecture that consists of multi-cells - each an aggregation\nof a number of floating gate transistors.", "date": "2012-06-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20120516-141137208", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20120516-141137208", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "funders": { "items": [ { "agency": "NSF", "grant_number": "ECCS-0801795" }, { "agency": "Binational Science Foundation (USA-Israel)", "grant_number": "2010075" } ] }, "other_numbering_system": { "items": [ { "id": "ETR115", "name": "Paradise" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr115.pdf", "url": "https://authors.library.caltech.edu/records/gxf0c-h9x26/files/etr115.pdf" }, "pub_year": "2012", "author_list": "En Gad, Eyal; Jiang, Anxiao (Andrew); et el." }, { "id": "https://authors.library.caltech.edu/records/6n5zz-gsa64", "eprint_id": 31274, "eprint_status": "archive", "datestamp": "2023-08-19 08:15:54", "lastmod": "2023-10-17 15:43:43", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Jiang-Anxiao-Andrew", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Zhou-Hongchao", "name": { "family": "Zhou", "given": "Hongchao" } }, { "id": "Wang-Zhiying", "name": { "family": "Wang", "given": "Zhiying" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Patterned Cells for Phase Change Memories", "ispublished": "unpub", "full_text_status": "public", "note": "Submitted - etr114.pdf
", "abstract": "Phase-change memory (PCM) is an emerging nonvolatile memory technology that promises very high performance.\nIt currently uses discrete cell levels to represent data, controlled\nby a single amorphous/crystalline domain in a cell. To improve\ndata density, more levels per cell are needed. There exist a number of challenges, including cell programming noise, drifting of\ncell levels, and the high power requirement for cell programming.\nIn this paper, we present a new cell structure called patterned cell, and explore its data representation schemes. Multiple\ndomains per cell are used, and their connectivity is used to\nstore data. We analyze its storage capacity, and study its error-correction capability and the construction of error-control codes.", "date": "2012-05-02", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20120502-130441311", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20120502-130441311", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "other_numbering_system": { "items": [ { "id": "ETR114", "name": "Paradise" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr114.pdf", "url": "https://authors.library.caltech.edu/records/6n5zz-gsa64/files/etr114.pdf" }, "pub_year": "2012", "author_list": "Jiang, Anxiao (Andrew); Zhou, Hongchao; et el." }, { "id": "https://authors.library.caltech.edu/records/n50yx-act24", "eprint_id": 31272, "eprint_status": "archive", "datestamp": "2023-08-19 08:15:50", "lastmod": "2023-10-17 15:43:39", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Zhou-H", "name": { "family": "Zhou", "given": "Hongchao" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Variable-level Cells for Nonvolatile Memories", "ispublished": "unpub", "full_text_status": "public", "abstract": "For many nonvolatile memories, \u2013 including flash\nmemories, phase-change memories, etc., \u2013 maximizing the storage\ncapacity is a key challenge. The existing method is to use multilevel cells (MLC) of more and more levels. The number of levels\nsupported by MLC is seriously constrained by the worst-case\nperformance of cell-programming noise and cell heterogeneity.\nIn this paper, we present variable-level cells (VLC), a new\nscheme for maximum storage capacity. It adaptively chooses the\nnumber of levels and the placement of the levels based on the\nactual programming performance. We derive its storage capacity,\nand present an optimal data representation scheme. We also study\nrewriting schemes for VLC, and present inner and outer bounds\nto its capacity region.", "date": "2012-05-02", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechAUTHORS:20120502-125850834", "official_url": "https://resolver.caltech.edu/CaltechAUTHORS:20120502-125850834", "rights": "No commercial reproduction, distribution, display or performance rights in this work are provided.", "other_numbering_system": { "items": [ { "id": "ETR113", "name": "Paradise" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr113.pdf", "url": "https://authors.library.caltech.edu/records/n50yx-act24/files/etr113.pdf" }, "pub_year": "2012", "author_list": "Jiang, Anxiao (Andrew); Zhou, Hongchao; et el." }, { "id": "https://authors.library.caltech.edu/records/xp404-dac89", "eprint_id": 26143, "eprint_status": "archive", "datestamp": "2023-08-23 16:45:02", "lastmod": "2023-10-24 16:15:29", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Zhou-Hongchao", "name": { "family": "Zhou", "given": "Hongchao" } }, { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Systematic Error-Correcting Codes for Rank Modulation", "ispublished": "unpub", "full_text_status": "public", "note": "Submitted - etr112.pdf
", "abstract": "The rank modulation scheme has been proposed recently for efficiently writing and storing data in nonvolatile\nmemories. Error-correcting codes are very important for rank\nmodulation; however, existing results have bee limited.\n\nIn this work, we explore a new approach, systematic error-correcting codes for rank modulation. Systematic codes have the benefits of enabling efficient information retrieval and potentially supporting more efficient encoding and decoding procedures. We study systematic codes for rank modulation equipped with the Kendall's \u03c4-distance. We present (k + 2, k) systematic codes for correcting one error, which have optimal rates unless perfect\ncodes exist. We also study the design of multi-error-correcting codes, and prove that for any 2 \u2264 k < n, there always exists an (n,k) systematic code of minimum distance\nn \u2212 k. Furthermore, we prove that for rank modulation, systematic codes achieve the same capacity as general error-correcting codes.", "date": "2011-07-14", "date_type": "published", "id_number": "CaltechPARADISE:2011.ETR112", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2011.ETR112", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "other_numbering_system": { "items": [ { "id": "ETR112", "name": "Paradise" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "doi": "10.48550/arXiv.1310.6817", "primary_object": { "basename": "etr112.pdf", "url": "https://authors.library.caltech.edu/records/xp404-dac89/files/etr112.pdf" }, "pub_year": "2011", "author_list": "Zhou, Hongchao; Jiang, Anxiao (Andrew); et el." }, { "id": "https://authors.library.caltech.edu/records/vz336-bdm65", "eprint_id": 26142, "eprint_status": "archive", "datestamp": "2023-08-19 07:28:43", "lastmod": "2023-10-24 16:15:27", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Wang-Zhiying", "name": { "family": "Wang", "given": "Zhiying" } }, { "id": "Tamo-I", "name": { "family": "Tamo", "given": "Itzhak" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "On Codes for Optimal Rebuilding Access", "ispublished": "unpub", "full_text_status": "public", "note": "We thank Dimitris Papailiopoulos, Alexandros Dimakis and\nViveck Cadambe for the inspiring discussions.", "abstract": "MDS (maximum distance separable) array codes\nare widely used in storage systems due to their computationally\nefficient encoding and decoding procedures. An MDS code with\nr redundancy nodes can correct any r erasures by accessing\n(reading) all the remaining information in both the systematic\nnodes and the parity (redundancy) nodes. However, in practice,\na single erasure is the most likely failure event; hence, a natural\nquestion is how much information do we need to access in order\nto rebuild a single storage node? We define the rebuilding ratio\nas the fraction of remaining information accessed during the\nrebuilding of a single erasure. In our previous work we showed\nthat the optimal rebuilding ratio of 1/r is achievable (using\nour newly constructed array codes) for the rebuilding of any\nsystematic node, however, all the information needs to be accessed\nfor the rebuilding of the parity nodes. Namely, constructing array\ncodes with a rebuilding ratio of 1/r was left as an open problem.\nIn this paper, we solve this open problem and present array codes\nthat achieve the lower bound of 1/r for rebuilding any single\nsystematic or parity node.", "date": "2011-07-08", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2011.ETR111", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2011.ETR111", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "doi": "10.48550/arXiv.1107.1627", "primary_object": { "basename": "etr111.pdf", "url": "https://authors.library.caltech.edu/records/vz336-bdm65/files/etr111.pdf" }, "pub_year": "2011", "author_list": "Wang, Zhiying; Tamo, Itzhak; et el." }, { "id": "https://authors.library.caltech.edu/records/vp0h3-kfs88", "eprint_id": 26141, "eprint_status": "archive", "datestamp": "2023-08-19 05:54:37", "lastmod": "2023-10-24 16:15:24", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Tamo-I", "name": { "family": "Tamo", "given": "Itzhak" } }, { "id": "Wang-Zhiying", "name": { "family": "Wang", "given": "Zhiying" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "MDS Array Codes with Optimal Rebuilding", "ispublished": "unpub", "full_text_status": "public", "note": "Submitted - etr110.pdf
", "abstract": "MDS array codes are widely used in storage systems\nto protect data against erasures. We address the rebuilding ratio\nproblem, namely, in the case of erasures, what is the the fraction\nof the remaining information that needs to be accessed in order\nto rebuild exactly the lost information? It is clear that when the\nnumber of erasures equals the maximum number of erasures\nthat an MDS code can correct then the rebuilding ratio is 1\n(access all the remaining information). However, the interesting\n(and more practical) case is when the number of erasures is\nsmaller than the erasure correcting capability of the code. For\nexample, consider an MDS code that can correct two erasures:\nWhat is the smallest amount of information that one needs to\naccess in order to correct a single erasure? Previous work showed\nthat the rebuilding ratio is bounded between 1/2 and 3/4 , however,\nthe exact value was left as an open problem. In this paper, we\nsolve this open problem and prove that for the case of a single\nerasure with a 2-erasure correcting code, the rebuilding ratio is\n1/2 . In general, we construct a new family of r-erasure correcting\nMDS array codes that has optimal rebuilding ratio of 1/r\nin the\ncase of a single erasure. Our array codes have efficient encoding\nand decoding algorithms (for the case r = 2 they use a finite field\nof size 3) and an optimal update property.", "date": "2011-03-18", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2011.ETR110", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2011.ETR110", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "doi": "10.48550/arXiv.1103.3737", "primary_object": { "basename": "etr110.pdf", "url": "https://authors.library.caltech.edu/records/vp0h3-kfs88/files/etr110.pdf" }, "pub_year": "2011", "author_list": "Tamo, Itzhak; Wang, Zhiying; et el." }, { "id": "https://authors.library.caltech.edu/records/6r95m-v4e81", "eprint_id": 26139, "eprint_status": "archive", "datestamp": "2023-08-19 05:35:37", "lastmod": "2023-10-24 16:15:22", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "En-Gad-E", "name": { "family": "En Gad", "given": "Eyal" } }, { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Compressed Encoding for Rank Modulation", "ispublished": "unpub", "full_text_status": "public", "note": "Submitted - etr108.pdf
", "abstract": "Rank modulation has been recently proposed as\na scheme for storing information in flash memories. While\nrank modulation has advantages in improving write speed and\nendurance, the current encoding approach is based on the \"push\nto the top\" operation that is not efficient in the general case. We\npropose a new encoding procedure where a cell level is raised to\nbe higher than the minimal necessary subset -instead of all - of\nthe other cell levels. This new procedure leads to a significantly\nmore compressed (lower charge levels) encoding. We derive an\nupper bound for a family of codes that utilize the proposed\nencoding procedure, and consider code constructions that achieve\nthat bound for several special cases.", "date": "2011-02-18", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2011.ETR108", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2011.ETR108", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "doi": "10.48550/arXiv.1108.2741", "primary_object": { "basename": "etr108.pdf", "url": "https://authors.library.caltech.edu/records/6r95m-v4e81/files/etr108.pdf" }, "pub_year": "2011", "author_list": "En Gad, Eyal; Jiang, Anxiao (Andrew); et el." }, { "id": "https://authors.library.caltech.edu/records/wdvya-sq235", "eprint_id": 26138, "eprint_status": "archive", "datestamp": "2023-08-19 05:35:32", "lastmod": "2023-10-24 16:15:20", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "En-Gad-E", "name": { "family": "En Gad", "given": "Eyal" } }, { "id": "Langberg-M", "name": { "family": "Langberg", "given": "Michael" }, "orcid": "0000-0002-7470-0718" }, { "id": "Schwartz-Moshe", "name": { "family": "Schwartz", "given": "Moshe" }, "orcid": "0000-0002-1449-0026" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Generalized Gray Codes for Local Rank Modulation", "ispublished": "unpub", "full_text_status": "public", "note": "This work was supported in part by ISF grant 134/10, ISF grant 480/08, the Open University of Israel's research fund (grant no. 46114), the NSF grant ECCS-0802107, and an NSF-NRI award.\n\nSubmitted - etr107.pdf
", "abstract": "We consider the local rank-modulation scheme in\nwhich a sliding window going over a sequence of real-valued\nvariables induces a sequence of permutations. Local rank-modulation\nis a generalization of the rank-modulation scheme,\nwhich has been recently suggested as a way of storing information\nin flash memory. \n\nWe study Gray codes for the local rank-modulation scheme\nin order to simulate conventional multi-level flash cells while\nretaining the benefits of rank modulation. Unlike the limited\nscope of previous works, we consider code constructions for the\nentire range of parameters including the code length, sliding\nwindow size, and overlap between adjacent windows. We show\nour constructed codes have asymptotically-optimal rate. We also\nprovide efficient encoding, decoding, and next-state algorithms.", "date": "2011-02-18", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2011.ETR107", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2011.ETR107", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "funders": { "items": [ { "agency": "Israeli Science Foundation", "grant_number": "134/10" }, { "agency": "Israeli Science Foundation", "grant_number": "480/08" }, { "agency": "Open University of Israel", "grant_number": "46614" }, { "agency": "NSF", "grant_number": "ECCS-0802107" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "doi": "10.48550/arXiv.1103.0317", "primary_object": { "basename": "etr107.pdf", "url": "https://authors.library.caltech.edu/records/wdvya-sq235/files/etr107.pdf" }, "pub_year": "2011", "author_list": "En Gad, Eyal; Langberg, Michael; et el." }, { "id": "https://authors.library.caltech.edu/records/ez3f7-4en24", "eprint_id": 26137, "eprint_status": "archive", "datestamp": "2023-08-19 05:30:48", "lastmod": "2023-10-24 16:15:18", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Lee-D", "name": { "family": "Lee", "given": "David" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Generating Probability Distributions using Multivalued Stochastic Relay Circuits", "ispublished": "unpub", "full_text_status": "public", "note": "The authors would like to thank Dan Wilhelm, Hongchao Zhou, and Ho-lin Chen for helpful discussions. They would also like to thank the Caltech SURF program, the Molecular Programming Project funded by the NSF Expeditions in Computing Program under grant CCF-0832824, and Aerospace Corporation for funding to make this research possible.\n\nSubmitted - etr106.pdf
", "abstract": "The problem of random number generation dates\nback to von Neumann's work in 1951. Since then, many algorithms\nhave been developed for generating unbiased bits from\ncomplex correlated sources as well as for generating arbitrary\ndistributions from unbiased bits. An equally interesting, but less\nstudied aspect is the structural component of random number\ngeneration as opposed to the algorithmic aspect. That is, given\na network structure imposed by nature or physical devices,\nhow can we build networks that generate arbitrary probability\ndistributions in an optimal way?\n\nIn this paper, we study the generation of arbitrary probability\ndistributions in multivalued relay circuits, a generalization in\nwhich relays can take on any of N states and the logical\n'and' and 'or' are replaced with 'min' and 'max' respectively.\nPrevious work was done on two-state relays. We generalize these\nresults, describing a duality property and networks that generate\narbitrary rational probability distributions. We prove that these\nnetworks are robust to errors and design a universal probability\ngenerator which takes input bits and outputs arbitrary binary\nprobability distributions.", "date": "2011-02-09", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2011.ETR106", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2011.ETR106", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "funders": { "items": [ { "agency": "Caltech Summer Undergraduate Research Fellowship (SURF)" }, { "agency": "NSF", "grant_number": "CCF-0832824" }, { "agency": "Aerospace Corporation" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "doi": "10.48550/arXiv.1102.1441", "primary_object": { "basename": "etr106.pdf", "url": "https://authors.library.caltech.edu/records/ez3f7-4en24/files/etr106.pdf" }, "pub_year": "2011", "author_list": "Lee, David and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/j1e3x-bk329", "eprint_id": 26135, "eprint_status": "archive", "datestamp": "2023-08-19 04:49:55", "lastmod": "2023-10-24 16:15:13", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Langberg-M", "name": { "family": "Langberg", "given": "Michael" }, "orcid": "0000-0002-7470-0718" }, { "id": "Schwartz-Moshe", "name": { "family": "Schwartz", "given": "Moshe" }, "orcid": "0000-0002-1449-0026" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Trajectory Codes for Flash Memory", "ispublished": "unpub", "full_text_status": "public", "keywords": "flash memory, asymmetric memory, rewriting, write-once memory, floating codes, buffer codes", "note": "This work was supported in part by the NSF CAREER Award CCF-0747415, the NSF grant ECCS-0802107, the ISF grant 480/08, the Open University of Israel Research Fund (grants no. 46109 and 101163), the GIF grant 2179-1785.10/2007, and the Caltech Lee Center for Advanced Networking.\n\nThe material in this paper was presented in part at the IEEE International\nSymposium on Information Theory (ISIT 2009), Seoul, South Korea, June\n2009\n\nSubmitted - etr104.pdf
", "abstract": "Flash memory is well-known for its inherent asymmetry: the flash-cell charge levels are easy to increase but are hard to decrease. In a general rewriting model, the stored data changes its value with certain patterns. The patterns of data updates are determined by the data structure and the application, and are independent of the constraints imposed by the storage medium. Thus, an appropriate coding scheme is needed so that the data changes can be updated and stored efficiently under the storage-medium's constraints.\nIn this paper, we define the general rewriting problem using a graph model. It extends many known rewriting models such as floating codes, WOM codes, buffer codes, etc. We present a new rewriting scheme for flash memories, called the trajectory code, for rewriting the stored data as many times as possible without block erasures. We prove that the trajectory code is asymptotically optimal in a wide range of scenarios.\nWe also present randomized rewriting codes optimized for expected performance (given arbitrary rewriting sequences). Our rewriting codes are shown to be asymptotically optimal.", "date": "2011-01-04", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2010.ETR104", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2010.ETR104", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "funders": { "items": [ { "agency": "NSF", "grant_number": "CCF-0747415" }, { "agency": "NSF", "grant_number": "ECCS-0802107" }, { "agency": "Israeli Science Foundation", "grant_number": "480/08" }, { "agency": "Open University of Israel", "grant_number": "46109" }, { "agency": "Open University of Israel", "grant_number": "101163" }, { "agency": "German-Israeli-Foundation", "grant_number": "2179-1785.10/2007" }, { "agency": "Caltech Lee Center for Advanced Networking" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "doi": "10.48550/arXiv.1012.5430", "primary_object": { "basename": "etr104.pdf", "url": "https://authors.library.caltech.edu/records/j1e3x-bk329/files/etr104.pdf" }, "pub_year": "2011", "author_list": "Jiang, Anxiao (Andrew); Langberg, Michael; et el." }, { "id": "https://authors.library.caltech.edu/records/vhtjs-aqs77", "eprint_id": 26136, "eprint_status": "archive", "datestamp": "2023-08-19 04:50:00", "lastmod": "2023-10-24 16:15:15", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "En-Gad-E", "name": { "family": "En Gad", "given": "Eyal" } }, { "id": "Langberg-M", "name": { "family": "Langberg", "given": "Michael" }, "orcid": "0000-0002-7470-0718" }, { "id": "Schwartz-Moshe", "name": { "family": "Schwartz", "given": "Moshe" }, "orcid": "0000-0002-1449-0026" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Constant-Weight Gray Codes for Local Rank Modulation", "ispublished": "unpub", "full_text_status": "public", "keywords": "Gray code, rank modulation, local rank modulation, permutations, flash memory", "note": "The material in this paper was presented in part at the IEEE International Symposium on Information Theory (ISIT 2010), Austin, TX, U.S.A., June 2010, and at the 26-th IEEE Convention of Electrical ans Electronics Engineers in Israel (IEEEI 2010), Eilat, Israel, November 2010.\nThis work was supported in part by ISF grant 134/10, ISF grant 480/08, the Open University of Israel's research fund (grant no. 46114), the NSF grant ECCS-0802107, and an NSF-NRI award.", "abstract": "We consider the local rank-modulation scheme in which a sliding window going over a sequence of real-valued variables induces a sequence of permutations. Local rank- modulation is a generalization of the rank-modulation scheme, which has been recently suggested as a way of storing information in flash memory.\nWe study constant-weight Gray codes for the local rank- modulation scheme in order to simulate conventional multi-level flash cells while retaining the benefits of rank modulation. We provide necessary conditions for the existence of cyclic and cyclic optimal Gray codes. We then specifically study codes of weight 2 and upper bound their efficiency, thus proving that there are no such asymptotically-optimal cyclic codes. In contrast, we study codes of weight 3 and efficiently construct codes which are asymptotically-optimal. We conclude with a construction of codes with asymptotically-optimal rate and weight asymptotically half the length, thus having an asymptotically-optimal charge difference between adjacent cells.", "date": "2010-12-31", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2010.ETR105", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2010.ETR105", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr105.pdf", "url": "https://authors.library.caltech.edu/records/vhtjs-aqs77/files/etr105.pdf" }, "pub_year": "2010", "author_list": "En Gad, Eyal; Langberg, Michael; et el." }, { "id": "https://authors.library.caltech.edu/records/h4jxr-xyf21", "eprint_id": 26134, "eprint_status": "archive", "datestamp": "2023-08-19 03:37:22", "lastmod": "2023-10-24 16:15:10", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Wang-Zhiying", "name": { "family": "Wang", "given": "Zhiying" } }, { "id": "Dimakis-A-G", "name": { "family": "Dimakis", "given": "Alexandros G." } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Rebuilding for Array Codes in Distributed Storage Systems", "ispublished": "unpub", "full_text_status": "public", "note": "Submitted - etr103.pdf
", "abstract": "In distributed storage systems that use coding, the issue of minimizing the communication required to rebuild a storage node after a failure arises. We consider the problem of repairing an erased node in a distributed storage system that uses an EVENODD code. EVENODD codes are maximum distance separable (MDS) array codes that are used to protect against erasures, and only require XOR operations for encoding and decoding. We show that when there are two redundancy nodes, to rebuild one erased systematic node, only 3=4 of the information needs to be transmitted. Interestingly, in many cases, the required disk I/O is also minimized.", "date": "2010-08-31", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2010.ETR103", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2010.ETR103", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "collection": "CaltechAUTHORS", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group", "value": "Parallel and Distributed Systems Group" } ] }, "primary_object": { "basename": "etr103.pdf", "url": "https://authors.library.caltech.edu/records/h4jxr-xyf21/files/etr103.pdf" }, "pub_year": "2010", "author_list": "Wang, Zhiying; Dimakis, Alexandros G.; et el." }, { "id": "https://authors.library.caltech.edu/records/07mcb-e2741", "eprint_id": 26133, "eprint_status": "archive", "datestamp": "2023-08-19 02:50:33", "lastmod": "2023-10-24 16:15:09", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Zhao-H", "name": { "family": "Zhao", "given": "Hongchao" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Efficiently Generating Random Bits from Finite State Markov Chains", "ispublished": "unpub", "full_text_status": "public", "keywords": "Random sequence, Random bits generation, Markov chain", "note": "This work was supported in part by the NSF Expeditions in Computing Program under grant CCF-0832824.", "abstract": "The problem of random number generation from an uncorrelated random source (of unknown probability distribution) dates back to von Neumann's 1951 work. Elias (1972) generalized von Neumann's scheme and showed how to achieve optimal efficiency in unbiased random bits generation. Hence, a natural question is what if the sources are correlated? Both Elias and Samuelson proposed methods for generating unbiased random bits in the case of correlated sources (of unknown probability distribution), specifically, they considered finite Markov chains. However, their proposed methods are not efficient or have implementation difficulties. Blum (1986) devised an algorithm for efficiently generating random bits from degree-2 finite Markov chains in expected linear time, however, his beautiful method is still far from optimality on information-efficiency. In this paper, we generalize Blum's algorithm to arbitrary degree finite Markov chains and combine it with Elias's method for efficient generation of unbiased bits. As a result, we provide the first known algorithm that generates unbiased random bits from an arbitrary finite Markov chain, operates in expected linear time and achieves the information-theoretic upper bound on efficiency.", "date": "2010-06-15", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2010.ETR102", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2010.ETR102", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr102.pdf", "url": "https://authors.library.caltech.edu/records/07mcb-e2741/files/etr102.pdf" }, "pub_year": "2010", "author_list": "Zhao, Hongchao and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/tmtgy-rqv10", "eprint_id": 26132, "eprint_status": "archive", "datestamp": "2023-08-19 01:35:47", "lastmod": "2023-10-24 16:15:06", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Zhou-Hongchao", "name": { "family": "Zhou", "given": "Hongchao" } }, { "id": "Chen-Ho-Lin", "name": { "family": "Chen", "given": "Ho-Lin" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "On the Synthesis of Stochastic Flow Networks", "ispublished": "unpub", "full_text_status": "public", "keywords": "Stochastic Flow Network, Graph, Feedback, Probability Synthesis", "note": "This work was supported in part by the NSF Expeditions in Computing Program under grant CCF-0832824.\n\nSubmitted - etr101.pdf
", "abstract": "A stochastic flow network is a directed graph with incoming edges (inputs) and outgoing edges (outputs), tokens enter through the input edges, travel stochastically in the network and can exit the network through the output edges. Each node in the network is a splitter, namely, a token can enter a node through an incoming edge and exit on one of the output edges according to a predefined probability distribution. We address the following synthesis question: Given a finite set of possible splitters and an arbitrary rational probability distribution, design a stochastic flow network, such that every token that enters the input edge will exit the outputs with the prescribed probability distribution. \n\nThe problem of probability synthesis dates back to von Neummann's 1951 work and was followed, among others, by Knuth and Yao in 1976, who demonstrated that arbitrary rational probabilities can be generated with tree networks; where minimizing the expected path length, the expected number of coin tosses in their paradigm, is the key consideration. Motivated by the synthesis of stochastic DNA based molecular systems, we focus on designing optimal size stochastic flow networks (the size of a network is the number of splitters). We assume that each splitter has two outgoing edges and is unbiased (probability 1/2 per output edge). We show that an arbitrary rational probability a/b with a \u2264 b \u2264 2^n can be realized by a stochastic flow network of size n, we also show that this is optimal. We note that our stochastic flow networks have feedback (cycles in the network), in fact, we demonstrate that feedback improves the expressibility of stochastic flow networks, since without feedback only probabilities of the form a/2^n (a an integer) can be realized.", "date": "2010-02-03", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2010.ETR101", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2010.ETR101", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "funders": { "items": [ { "agency": "NSF", "grant_number": "CCF-0832824" } ] }, "collection": "CaltechAUTHORS", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group", "value": "Parallel and Distributed Systems Group" } ] }, "doi": "10.48550/arXiv.1209.0724", "primary_object": { "basename": "etr101.pdf", "url": "https://authors.library.caltech.edu/records/tmtgy-rqv10/files/etr101.pdf" }, "pub_year": "2010", "author_list": "Zhou, Hongchao; Chen, Ho-Lin; et el." }, { "id": "https://authors.library.caltech.edu/records/nemx7-1bs28", "eprint_id": 26131, "eprint_status": "archive", "datestamp": "2023-08-19 01:28:57", "lastmod": "2023-10-24 16:15:04", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Langberg-M", "name": { "family": "Langberg", "given": "Michael" }, "orcid": "0000-0002-7470-0718" }, { "id": "Mateescu-R", "name": { "family": "Mateescu", "given": "Robert" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Data Movement and Aggregation in Flash Memories", "ispublished": "unpub", "full_text_status": "public", "abstract": "NAND flash memories have become the most widely used type of non-volatile memories. In a NAND flash memory, every block of memory cells consists of numerous pages, and rewriting a single page requires the whole block to be erased. As block erasures significantly reduce the longevity, speed and power efficiency of flash memories, it is critical to minimize the number of erasures when data are reorganized. This leads to the data movement problem, where data need to be switched in blocks, and the objective is to minimize the number of block erasures. It has been shown that optimal solutions can be obtained by coding. However, coding-based algorithms with the minimum coding complexity still remain an important topic to study. \n\nIn this paper, we present a very efficient data movement algorithm with coding over GF(2) and with the minimum storage requirement. We also study data movement with more auxiliary blocks and present its corresponding solution. Furthermore, we extend the study to the data aggregation problem, where data can not only be moved but also aggregated. We present both non-coding and coding-based solutions, and rigorously prove the performance gain by using coding.", "date": "2010-01-25", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2010.ETR100", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2010.ETR100", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "collection": "CaltechAUTHORS", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group", "value": "Parallel and Distributed Systems Group" } ] }, "primary_object": { "basename": "etr100.pdf", "url": "https://authors.library.caltech.edu/records/nemx7-1bs28/files/etr100.pdf" }, "pub_year": "2010", "author_list": "Jiang, Anxiao (Andrew); Langberg, Michael; et el." }, { "id": "https://authors.library.caltech.edu/records/xbgvp-n7v04", "eprint_id": 26130, "eprint_status": "archive", "datestamp": "2023-08-19 00:49:08", "lastmod": "2023-10-24 16:15:02", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Riedel-M-D", "name": { "family": "Riedel", "given": "Marc D." }, "orcid": "0000-0002-3318-346X" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Cyclic Boolean circuits", "ispublished": "unpub", "full_text_status": "public", "keywords": "Boolean circuits, Boolean functions, combinational circuits, cyclic circuits, DAG, cycles, loops, feedback", "note": "This work is partially supported by an NSF CAREER Award (grant CCF0845650), by the NSF Expeditions in Computing Program (grant CCF-0832824), by a grant from the MARCO Focus Center Research Program on Functional Engineered Nano-Architectonics (FENA), and by the Caltech Lee Center for Advanced Networking. \n\nPreprint submitted to Discrete Mathematics.", "abstract": "A Boolean circuit is a collection of gates and wires that performs a mapping from Boolean inputs to Boolean outputs. The accepted wisdom is that such circuits must have acyclic (i.e., loop-free or feed-forward) topologies. In fact, the model is often defined this way \u2013 as a directed acyclic graph (DAG). And yet simple examples suggest that this is incorrect. We advocate that Boolean circuits should have cyclic topologies (i.e., loops or feedback paths). In other work, we demonstrated the practical implications of this view: digital circuits can be designed with fewer gates if they contain cycles. In this paper, we explore the theoretical underpinnings of the idea. We show that the complexity of implementing Boolean functions can be lower with cyclic topologies than with acyclic topologies. With examples, we show that certain Boolean functions can be implemented by cyclic circuits with as little as one-half the number gates that are required by equivalent acyclic circuits.", "date": "2009-12-08", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2009.ETR099", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2009.ETR099", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "collection": "CaltechAUTHORS", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group", "value": "Parallel and Distributed Systems Group" } ] }, "primary_object": { "basename": "etr099.pdf", "url": "https://authors.library.caltech.edu/records/xbgvp-n7v04/files/etr099.pdf" }, "pub_year": "2009", "author_list": "Riedel, Marc D. and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/90s7z-gkx15", "eprint_id": 26129, "eprint_status": "archive", "datestamp": "2023-08-19 00:37:03", "lastmod": "2023-10-24 16:15:00", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Cassuto-Y", "name": { "family": "Cassuto", "given": "Yuval" }, "orcid": "0000-0001-6369-6699" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Low-Complexity Codes for Random and Clustered High-Order Failures in Storage Arrays", "ispublished": "unpub", "full_text_status": "public", "keywords": "Array codes, clustered erasures, correlated failures, storage arrays", "note": "This work was supported in part by the Caltech Lee Center for Advanced Networking.", "abstract": "RC (Random/Clustered) codes are a new efficient array-code family for recovering from 4-erasures. RC codes correct most 4-erasures, and essentially all 4-erasures that are clustered. Clustered erasures are introduced as a new erasure model for storage arrays. This model draws its motivation from correlated device failures, that are caused by physical proximity of devices, or by age proximity of endurance-limited solid-state drives. The reliability of storage arrays that employ RC codes is analyzed and compared to known codes. The new RC code is significantly more efficient, in all practical implementation factors, than the best known 4-erasure correcting MDS code. These factors include: small-write update-complexity, full-device update-complexity, decoding complexity and number of supported devices in the array.", "date": "2009-11-27", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2009.ETR098", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2009.ETR098", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr098.pdf", "url": "https://authors.library.caltech.edu/records/90s7z-gkx15/files/etr098.pdf" }, "related_objects": [ { "basename": "etr098v2.pdf", "url": "https://authors.library.caltech.edu/records/90s7z-gkx15/files/etr098v2.pdf" } ], "pub_year": "2009", "author_list": "Cassuto, Yuval and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/yq8rd-mzk34", "eprint_id": 26125, "eprint_status": "archive", "datestamp": "2023-08-20 00:49:09", "lastmod": "2023-10-20 23:02:03", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Mateescu-R", "name": { "family": "Mateescu", "given": "Robert" } }, { "id": "Yaakobi-E", "name": { "family": "Yaakobi", "given": "Eitan" }, "orcid": "0000-0002-9851-5234" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" }, { "id": "Siegel-P-H", "name": { "family": "Siegel", "given": "Paul H." }, "orcid": "0000-0002-2539-4646" }, { "id": "Vardy-A", "name": { "family": "Vardy", "given": "Alexander" } }, { "id": "Wolf-J-K", "name": { "family": "Wolf", "given": "Jack K." } } ] }, "title": "Storage Coding for Wear Leveling in Flash Memories", "ispublished": "unpub", "full_text_status": "public", "note": "Submitted - etr094.pdf
", "abstract": "NAND flash memories are currently the most widely\nused type of flash memories. In a NAND flash memory, although a\ncell block consists of many pages, to rewrite one page, the whole\nblock needs to be erased and reprogrammed. Block erasures\ndetermine the longevity and efficiency of flash memories. So when\ndata is frequently reorganized, which can be characterized as a\ndata movement process, how to minimize block erasures becomes\nan important challenge. In this paper, we show that coding\ncan significantly reduce block erasures for data movement, and\npresent several optimal or nearly optimal algorithms. While the\nsorting-based non-coding schemes require O(n log n) erasures to\nmove data among n blocks, coding-based schemes use only O(n)\nerasures and also optimize the utilization of storage space.", "date": "2009-09-21", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2009.ETR094", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2009.ETR094", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr094.pdf", "url": "https://authors.library.caltech.edu/records/yq8rd-mzk34/files/etr094.pdf" }, "pub_year": "2009", "author_list": "Jiang, Anxiao (Andrew); Mateescu, Robert; et el." }, { "id": "https://authors.library.caltech.edu/records/2gmxq-03v21", "eprint_id": 26128, "eprint_status": "archive", "datestamp": "2023-08-20 02:13:26", "lastmod": "2023-10-24 16:14:58", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Langberg-M", "name": { "family": "Langberg", "given": "Michael" }, "orcid": "0000-0002-7470-0718" }, { "id": "Mateesu-R", "name": { "family": "Mateesu", "given": "Robert" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Data Movement in Flash Memories", "ispublished": "unpub", "full_text_status": "public", "abstract": "NAND flash memories are the most widely used non-volatile memories, and data movement is common in flash storage\nsystems. We study data movement solutions that minimize the number of block erasures, which are very important for the\nefficiency and longevity of flash memories. To move data among n blocks with the help of \u0394 auxiliary blocks, where every block\ncontains m pages, we present algorithms that use \u03b8(n \u2022 min{m, log_\u0394 n}) erasures without the tool of coding. We prove this is\nalmost the best possible for non-coding solutions by presenting a nearly matching lower bound. Optimal data movement can be\nachieved using coding, where only \u03b8(n) erasures are needed. We present a coding-based algorithm, which has very low coding\ncomplexity, for optimal data movement. We further show the NP hardness of both coding-based and non-coding schemes when\nthe objective is to optimize data movement on a per instance basis.", "date": "2009-07-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2009.ETR097", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2009.ETR097", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr097.pdf", "url": "https://authors.library.caltech.edu/records/2gmxq-03v21/files/etr097.pdf" }, "pub_year": "2009", "author_list": "Jiang, Anxiao (Andrew); Langberg, Michael; et el." }, { "id": "https://authors.library.caltech.edu/records/80cap-8jm07", "eprint_id": 26120, "eprint_status": "archive", "datestamp": "2023-08-20 01:44:35", "lastmod": "2023-10-24 16:14:43", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Wilhelm-D", "name": { "family": "Wilhelm", "given": "Daniel" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Stochastic Switching Circuit Synthesis", "ispublished": "unpub", "full_text_status": "public", "note": "Daniel Wilhelm was supported by the U.S. Department of Homeland Security (DHS) Scholarship and Fellowship Program, administered by the Oak Ridge Institute for Science and Education (ORISE). \n\nAlso available http://www.paradise.caltech.edu/papers/etr089.pdf", "abstract": "In his 1938 Master's Thesis, Shannon demonstrated that any Boolean function can be realized by a switching relay circuit, leading to the development of deterministic digital logic. Here, we replace each classical switch with a probabilistic switch (pswitch). We present algorithms for synthesizing circuits closed with a desired probability, including an algorithm that generates optimal size circuits for any binary fraction. We also introduce a new duality property for series-parallel stochastic switching circuits. Finally, we construct a universal probability generator which maps deterministic inputs to arbitrary probabilistic outputs. Potential applications exist in the analysis and design of stochastic networks in biology and engineering.", "date": "2009-05-19", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2008.ETR089", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2008.ETR089", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr089.pdf", "url": "https://authors.library.caltech.edu/records/80cap-8jm07/files/etr089.pdf" }, "pub_year": "2009", "author_list": "Wilhelm, Daniel and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/mkc70-5fd26", "eprint_id": 26126, "eprint_status": "archive", "datestamp": "2023-08-20 01:22:09", "lastmod": "2023-10-24 16:14:54", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Schwartz-Moshe", "name": { "family": "Schwartz", "given": "Moshe" }, "orcid": "0000-0002-1449-0026" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Correcting Charge-Constrained Errors in the Rank-Modulation Scheme", "ispublished": "unpub", "full_text_status": "public", "keywords": "flash memory, rank modulation, errorcorrecting codes, permutations, metric embeddings, Kendall's \u03c4-metric", "abstract": "We investigate error-correcting codes for a novel storage technology for flash memories, the rank-modulation scheme. In this scheme, a set of n cells stores information in the permutation induced by the different charge levels of the individual cells. The resulting scheme eliminates the need for discrete cell levels, overcomes overshoot errors when programming cells (a serious problem that reduces the writing speed), and mitigates the problem of asymmetric errors. \n\nIn this paper we study the properties of error-correcting codes for charge-constrained errors in the rank-modulation scheme. In this error model the number of errors corresponds to the minimal number of adjacent transpositions required to change a given stored permutation to another erroneous one \u2013 a distance measure known as Kendall's \u03c4-distance. \n\nWe show bounds on the size of such codes, and use metric-embedding techniques to give constructions which translate a\nwealth of knowledge of binary codes in the Hamming metric as well as q-ary codes in the Lee metric, to codes over permutations in Kendall's \u03c4-metric. Specifically, the one-error-correcting codes we construct are at least half the ball-packing upper bound.", "date": "2009-04", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2009.ETR095", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2009.ETR095", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr095.pdf", "url": "https://authors.library.caltech.edu/records/mkc70-5fd26/files/etr095.pdf" }, "pub_year": "2009", "author_list": "Jiang, Anxiao (Andrew); Schwartz, Moshe; et el." }, { "id": "https://authors.library.caltech.edu/records/915ad-wt606", "eprint_id": 26127, "eprint_status": "archive", "datestamp": "2023-08-20 01:22:14", "lastmod": "2023-10-24 16:14:56", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Langberg-M", "name": { "family": "Langberg", "given": "Michael" }, "orcid": "0000-0002-7470-0718" }, { "id": "Schwartz-Moshe", "name": { "family": "Schwartz", "given": "Moshe" }, "orcid": "0000-0002-1449-0026" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Universal Rewriting in Constrained Memories", "ispublished": "unpub", "full_text_status": "public", "note": "This work was supported in part by the NSF CAREER\nAward CCF-0747415, the NSF grant ECCS-0802107, the\nISF grant 480/08, the GIF grant 2179-1785.10/2007, and the\nCaltech Lee Center for Advanced Networking.", "abstract": "A constrained memory is a storage device whose elements change their states under some constraints. A typical example is flash memories, in which cell levels are easy to increase but hard to decrease. In a general rewriting model, the stored data changes with some pattern determined by the application. In a constrained memory, an appropriate representation is needed for the stored data to enable efficient rewriting. \n\nIn this paper, we define the general rewriting problem using a graph model. This model generalizes many known rewriting models such as floating codes, WOM codes, buffer codes, etc. We present a novel rewriting scheme for the flash-memory model and prove it is asymptotically optimal in a wide range of scenarios. \n\nWe further study randomization and probability distributions to data rewriting and study the expected performance. We present a randomized code for all rewriting sequences and a deterministic code for rewriting following any i.i.d. distribution. Both codes are shown to be optimal asymptotically.", "date": "2009-04", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2009.ETR096", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2009.ETR096", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr096.pdf", "url": "https://authors.library.caltech.edu/records/915ad-wt606/files/etr096.pdf" }, "pub_year": "2009", "author_list": "Jiang, Anxiao (Andrew); Langberg, Michael; et el." }, { "id": "https://authors.library.caltech.edu/records/3bvx9-zp442", "eprint_id": 26124, "eprint_status": "archive", "datestamp": "2023-08-20 00:50:31", "lastmod": "2023-10-24 16:14:52", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Zhou-H", "name": { "family": "Zhou", "given": "Hongchao" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "On the Expressibility of Stochastic Switching Circuits", "ispublished": "unpub", "full_text_status": "public", "note": "The authors would like to thank Dan Wilhelm for discussions and assistance.", "abstract": "Stochastic switching circuits are relay circuits that consist of stochastic switches (that we call pswitches). We study the expressive power of these circuits; in particular, we address the following basic question: given an arbitrary integer q, and a pswitch set {1/q, 2/q, ..., (q\u20131)/q }, can we realize any rational probability with denominator q n (for arbitrary n) by a simple series-parallel stochastic switching circuit? In this paper, we generalized previous results and prove that when q is a multiple of 2 or 3 the answer is positive. We also show that when q is a prime number the answer is negative. In addition, we propose a greedy algorithm to realize desired reachable probabilities, and thousands of experiments show that this algorithm can achieve almost optimal size. Finally, we prove that any desired probability can be approximated well by a linear size circuit.", "date": "2009-02-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2009.ETR093", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2009.ETR093", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr093.pdf", "url": "https://authors.library.caltech.edu/records/3bvx9-zp442/files/etr093.pdf" }, "pub_year": "2009", "author_list": "Zhou, Hongchao and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/zae12-vg894", "eprint_id": 26123, "eprint_status": "archive", "datestamp": "2023-08-20 00:38:52", "lastmod": "2023-10-24 16:14:50", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Loh-P-L", "name": { "family": "Loh", "given": "Po-Ling" } }, { "id": "Zhou-H", "name": { "family": "Zhou", "given": "Hongchao" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "The Robustness of Stochastic Switching Networks", "ispublished": "unpub", "full_text_status": "public", "note": "This work was supported in part by the NSF Expeditions in Computing Program under grant CCF-0832824. The authors would also like to thank the Caltech Summer Undergraduate Research Fellowship (SURF) program for its support in funding this research, and Dan Wilhelm for his comments and suggestions in revising the paper.", "abstract": "Many natural systems, including chemical and biological systems, can be modeled using stochastic switching circuits. These circuits consist of stochastic switches, called pswitches, which operate with a fixed probability of being open or closed. We study the effect caused by introducing an error of size \u2208 to each pswitch in a stochastic circuit. We analyze two constructions \u2013 simple series-parallel and general series-parallel circuits \u2013 and prove that simple series-parallel circuits are robust to small error perturbations, while general series-parallel circuits are not. Specifically, the total error introduced by perturbations of size less than \u2208 is bounded by a constant multiple of \u2208 in a simple series-parallel circuit, independent of the size of the circuit. However, the same result does not hold in the case of more general series-parallel circuits. In the case of a general stochastic circuit, we prove that the overall error probability is bounded by a linear function of the number of pswitches.", "date": "2009-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2009.ETR092", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2009.ETR092", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr092.pdf", "url": "https://authors.library.caltech.edu/records/zae12-vg894/files/etr092.pdf" }, "pub_year": "2009", "author_list": "Loh, Po-Ling; Zhou, Hongchao; et el." }, { "id": "https://authors.library.caltech.edu/records/pe2zr-nrj54", "eprint_id": 26122, "eprint_status": "archive", "datestamp": "2023-08-20 00:36:56", "lastmod": "2023-10-24 16:14:48", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Wang-Zhiying", "name": { "family": "Wang", "given": "Zhiying" } }, { "id": "Jiang-Anxiao-Andrew", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "On the capacity of bounded rank modulation for flash memories", "ispublished": "unpub", "full_text_status": "public", "note": "Submitted - etr091.pdf
", "abstract": "Rank modulation has been recently introduced as a new information representation scheme for flash memories.\nGiven the charge levels of a group of flash cells, sorting\nis used to induce a permutation, which in turn represents\ndata. Motivated by the lower sorting complexity of smaller\ncell groups, we consider bounded rank modulation, where\na sequence of permutations of given sizes are used to\nrepresent data. We study the capacity of bounded rank\nmodulation under the condition that permutations can\noverlap for higher capacity.", "date": "2009-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2008.ETR091", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2008.ETR091", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.\n", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr091.pdf", "url": "https://authors.library.caltech.edu/records/pe2zr-nrj54/files/etr091.pdf" }, "pub_year": "2009", "author_list": "Wang, Zhiying; Jiang, Anxiao (Andrew); et el." }, { "id": "https://authors.library.caltech.edu/records/gf8h4-ta232", "eprint_id": 26121, "eprint_status": "archive", "datestamp": "2023-08-19 23:39:34", "lastmod": "2023-10-24 16:14:45", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Cook-M", "name": { "family": "Cook", "given": "Matthew" } }, { "id": "Soloveichik-D", "name": { "family": "Soloveichik", "given": "David" }, "orcid": "0000-0002-2585-4120" }, { "id": "Winfree-E", "name": { "family": "Winfree", "given": "Erik" }, "orcid": "0000-0002-5899-7523" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Programmability of Chemical Reaction Networks", "ispublished": "unpub", "full_text_status": "public", "note": "The research was supported in part by the \"Alpha Project\" at the Center for Genomic Experimentation and Computation, an NIH Center of Excellence (grant number P50 HG02370), as well as NSF Grants No. 0523761 and 0728703 to EW and NIMH Training Grant MH19138-15.\n\nSubmitted - etr090.pdf
", "abstract": "Motivated by the intriguing complexity of biochemical circuitry within individual cells we study Stochastic Chemical Reaction Networks (SCRNs), a formal model that considers a set of chemical reactions acting on a finite number of molecules in a well-stirred solution according to standard chemical kinetics equations. SCRNs have been widely used for describing naturally occurring (bio)chemical systems, and with the advent of synthetic biology they become a promising language for the design of artificial biochemical circuits. Our interest here is the computational power of SCRNs and how they relate to more conventional models of computation. We survey known connections and give new connections between SCRNs and Boolean Logic Circuits, Vector Addition Systems, Petri Nets, Gate Implementability, Primitive Recursive Functions, Register Machines, Fractran, and Turing Machines. A theme to these investigations is the thin line between decidable and undecidable questions about SCRN behavior.", "date": "2008-09-23", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2008.ETR090", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2008.ETR090", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "funders": { "items": [ { "agency": "NIH", "grant_number": "P50 HG02370" }, { "agency": "NSF", "grant_number": "CCF-0523761" }, { "agency": "NSF", "grant_number": "CCF-0728703" }, { "agency": "NIH Predoctoral Fellowship", "grant_number": "MH19138-15" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr090.pdf", "url": "https://authors.library.caltech.edu/records/gf8h4-ta232/files/etr090.pdf" }, "pub_year": "2008", "author_list": "Cook, Matthew; Soloveichik, David; et el." }, { "id": "https://authors.library.caltech.edu/records/ddvmx-zv463", "eprint_id": 26119, "eprint_status": "archive", "datestamp": "2023-08-22 12:38:00", "lastmod": "2023-10-24 16:14:41", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Cassuto-Y", "name": { "family": "Cassuto", "given": "Yuval" }, "orcid": "0000-0001-6369-6699" }, { "id": "Schwartz-Moshe", "name": { "family": "Schwartz", "given": "Moshe" }, "orcid": "0000-0002-1449-0026" }, { "id": "Bohossian-V", "name": { "family": "Bohossian", "given": "Vasken" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Codes for Asymmetric Limited-Magnitude Errors with Application to Multi-Level Flash Memories", "ispublished": "unpub", "full_text_status": "public", "keywords": "error-correcting codes; asymmetric limited-magnitude\nerrors", "note": "This work was supported in part by the Caltech Lee Center for Advanced Networking.\n\nAlso available http://www.paradise.caltech.edu/papers/etr088.pdf", "abstract": "Several physical effects that limit the reliability and\nperformance of Multilevel Flash Memories induce errors that\nhave low magnitudes and are dominantly asymmetric. This paper studies block codes for asymmetric limited-magnitude errors over q-ary channels. We propose code constructions and bounds for such channels when the number of errors is bounded by t and the error magnitudes are bounded by \u0841. The constructions utilize known codes for symmetric errors, over small alphabets, to protect large-alphabet symbols from asymmetric limited-magnitude errors. The encoding and decoding of these codes are performed over the small alphabet whose size depends only on the maximum error magnitude and is independent of the alphabet size of the outer code. Moreover, the size of the codes is shown\nto exceed the sizes of known codes (for related error models), and asymptotic rate-optimality results are proved. Extensions of the construction are proposed to accommodate variations on the error model and to include systematic codes as a benefit to practical implementation.", "date": "2008-08", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2008.ETR088", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2008.ETR088", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr088.pdf", "url": "https://authors.library.caltech.edu/records/ddvmx-zv463/files/etr088.pdf" }, "related_objects": [ { "basename": "etr088v2.pdf", "url": "https://authors.library.caltech.edu/records/ddvmx-zv463/files/etr088v2.pdf" } ], "pub_year": "2008", "author_list": "Cassuto, Yuval; Schwartz, Moshe; et el." }, { "id": "https://authors.library.caltech.edu/records/616vy-hw290", "eprint_id": 26118, "eprint_status": "archive", "datestamp": "2023-08-19 22:34:04", "lastmod": "2023-10-24 16:14:39", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Joint Coding for Flash Memory Storage", "ispublished": "unpub", "full_text_status": "public", "abstract": "Flash memory is an electronic non-volatile memory with wide applications. Due to the substantial impact of block erasure operations on the speed, reliability and longevity of flash memories, writing schemes that enable data to be modified numerous times without incurring the block erasure is desirable. This requirement is addressed by floating codes, a coding scheme that jointly stores and rewrites data and maximizes the rewriting capability of flash memories. In this paper, we present several new floating code constructions. They include both codes with specific parameters and general code constructions that are asymptotically optimal. We also present bounds to the performance of floating codes.", "date": "2008-04-25", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2008.ETR087", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2008.ETR087", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr087.pdf", "url": "https://authors.library.caltech.edu/records/616vy-hw290/files/etr087.pdf" }, "pub_year": "2008", "author_list": "Jiang, Anxiao (Andrew) and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/awqbq-dvx67", "eprint_id": 26116, "eprint_status": "archive", "datestamp": "2023-08-19 22:02:03", "lastmod": "2023-10-24 16:14:35", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Mateescu-R", "name": { "family": "Mateescu", "given": "Robert" } }, { "id": "Schwartz-Moshe", "name": { "family": "Schwartz", "given": "Moshe" }, "orcid": "0000-0002-1449-0026" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Rank Modulation for Flash Memories", "ispublished": "unpub", "full_text_status": "public", "abstract": "We explore a novel data representation scheme for multi-level flash memory cells, in which a set of n cells stores information in the permutation induced by the different charge levels of the individual cells. The only allowed charge-placement mechanism is a \"push-to-the-top\" operation which takes a single cell of the set and makes it the top-charged cell. The resulting scheme eliminates the need for discrete cell levels, as well as overshoot errors, when programming cells. \n\nWe present unrestricted Gray codes spanning all possible n-cell states and using only \"push-to-the-top\" operations, and also construct balanced Gray codes. We also investigate optimal rewriting schemes for translating arbitrary input alphabet into n-cell states which minimize the number of programming operations.", "date": "2008-01-18", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2008.ETR086", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2008.ETR086", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr086.pdf", "url": "https://authors.library.caltech.edu/records/awqbq-dvx67/files/etr086.pdf" }, "pub_year": "2008", "author_list": "Jiang, Anxiao (Andrew); Mateescu, Robert; et el." }, { "id": "https://authors.library.caltech.edu/records/f308m-93262", "eprint_id": 26115, "eprint_status": "archive", "datestamp": "2023-08-22 10:53:26", "lastmod": "2023-10-23 17:16:41", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Soloveichik-D", "name": { "family": "Soloveichik", "given": "David" }, "orcid": "0000-0002-2585-4120" }, { "id": "Cook-M", "name": { "family": "Cook", "given": "Matthew" } }, { "id": "Winfree-E", "name": { "family": "Winfree", "given": "Erik" }, "orcid": "0000-0002-5899-7523" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Computation with Finite Stochastic Chemical Reaction Networks", "ispublished": "unpub", "full_text_status": "public", "keywords": "stochastic chemical kinetics; molecular counts; Turing-universal computation; probabilistic computation", "note": "We thank G. Zavattaro for pointing out an error in an earlier version of this manuscript. This work is supported in part by the \"Alpha Project\" at the Center for Genomic Experimentation and Computation, an NIH Center of Excellence (grant no. P50 HG02370), as well as NSF Grant No. 0523761 and NIMH Training Grant MH19138-15. \n\n(Original version: September, 2007)\n\nPublished as: \n\nDavid Soloveichik, Matthew Cook, Erik Winfree, and Jehoshua Bruck (2008) Computation with finite stochastic chemical reaction networks. Natural Computing DOI: 10.1007/s11047-008-9067-y\n\nUpdated - etr085v2.pdf
", "abstract": "A highly desired part of the synthetic biology toolbox is an embedded chemical microcontroller, capable of autonomously following a logic program specified by a set of instructions, and interacting with its cellular environment. Strategies for incorporating logic in aqueous chemistry have focused primarily on implementing components, such as logic gates, that are composed into larger circuits, with each logic gate in the circuit corresponding to one or more molecular species. With this paradigm, designing and producing new molecular species is necessary to perform larger computations. An alternative approach begins by noticing that chemical systems on the small scale are fundamentally discrete and stochastic. In particular, the exact molecular counts of each molecular species present, is an intrinsically available form of information. This might appear to be a very weak form of information, perhaps quite difficult for computations to utilize. Indeed, it has been shown that error-free Turing universal computation is impossible in this setting. Nevertheless, we show a design of a chemical computer that achieves fast and reliable Turing-universal computation using molecular counts. Our scheme uses only a small number of different molecular species to do computation of arbitrary complexity. The total probability of error of the computation can be made arbitrarily small (but not zero) by adjusting the initial molecular counts of certain species. While physical implementations would be difficult, these results demonstrate that molecular counts can be a useful form of information for small molecular systems such as those operating within cellular environments.", "date": "2007-09-19", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2007.ETR085", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2007.ETR085", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "funders": { "items": [ { "agency": "NIH", "grant_number": "P50 HG02370" }, { "agency": "NSF", "grant_number": "CCF-0523761" }, { "agency": "NIH Predoctoral Fellowship", "grant_number": "MH19138-15" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr085v2.pdf", "url": "https://authors.library.caltech.edu/records/f308m-93262/files/etr085v2.pdf" }, "pub_year": "2007", "author_list": "Soloveichik, David; Cook, Matthew; et el." }, { "id": "https://authors.library.caltech.edu/records/2y7rc-55t61", "eprint_id": 26114, "eprint_status": "archive", "datestamp": "2023-08-19 20:18:11", "lastmod": "2023-10-24 16:14:33", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Langberg-M", "name": { "family": "Langberg", "given": "Michael" }, "orcid": "0000-0002-7470-0718" }, { "id": "Schwartz-Moshe", "name": { "family": "Schwartz", "given": "Moshe" }, "orcid": "0000-0002-1449-0026" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Distributed Broadcasting and Mapping Protocols in Directed Anonymous Networks", "ispublished": "unpub", "full_text_status": "public", "keywords": "Anonymous networks, directed networks, distributed protocols", "note": "This work was supported in part by the Caltech Lee Center for Advanced Networking and by NSF grant ANI-0322475. \n\nAlso available from http://www.paradise.caltech.edu/papers/etr084.pdf", "abstract": "We initiate the study of distributed protocols over directed anonymous networks that are not necessarily strongly connected. In such networks, nodes are aware only of their incoming and outgoing edges, have no unique identity, and have no knowledge of the network topology or even bounds on its parameters, like the number of nodes or the network diameter. Anonymous networks are of interest in various settings such as wireless ad-hoc networks and peer to peer networks. Our goal is to create distributed protocols that reduce the uncertainty by distributing the knowledge of the network topology to all the nodes. \n\nWe consider two basic protocols: broadcasting and unique label assignment. These two protocols enable a complete mapping of the network and can serve as key building blocks in more advanced protocols. We develop distributed asynchronous protocols as well as derive lower bounds on their communication complexity, total bandwidth complexity, and node label complexity. The resulting lower bounds are sometimes surprisingly high, exhibiting the complexity of topology extraction in directed anonymous networks.", "date": "2007-06", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2007.ETR084", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2007.ETR084", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr084.pdf", "url": "https://authors.library.caltech.edu/records/2y7rc-55t61/files/etr084.pdf" }, "pub_year": "2007", "author_list": "Langberg, Michael; Schwartz, Moshe; et el." }, { "id": "https://authors.library.caltech.edu/records/kzd49-t8346", "eprint_id": 26113, "eprint_status": "archive", "datestamp": "2023-08-19 19:59:35", "lastmod": "2023-10-24 16:14:31", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Bohassian-V", "name": { "family": "Bohassian", "given": "Vasken" } }, { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Buffer Coding for Asymmetric Multi-Level Memory", "ispublished": "unpub", "full_text_status": "public", "note": "This work was supported in part by the Lee Center for Advanced Networking at the California Institute of Technology. \n\nAlso available from http://www.paradise.caltech.edu/papers/etr083.pdf", "abstract": "Certain storage media such as flash memories use write-asymmetric, multi-level storage elements. In such media, data is stored in a multi-level memory cell the contents of which can only be increased, or reset. The reset operation is expensive and should be delayed as much as possible. Mathematically, we consider the problem of writing a binary sequence into write-asymmetric q-ary cells, while recording the last r bits written. We want to maximize t, the number of possible writes, before a reset is needed. We introduce the term Buffer Code, to describe the solution to this problem. A buffer code is a code that remembers the r most recent values of a variable. We present the construction of a single-cell (n = 1) buffer code that can store a binary (l = 2) variable with t = [q/2^(r - 1)] + r - 2 and a universal upper bound to the number of rewrites that a single-cell buffer code can have: ..... We also show a binary buffer code with arbitrary n, q, r, namely, the code uses n q-ary cells to remember the r most recent values of one binary variable. The code can rewrite the variable times, which is asymptotically optimal in q and n. . We then extend the code construction for the case r = 2, and obtain a code that can rewrite the variable t = (q - 1)(n - 2) + 1 times. When q = 2, the code is strictly optimal.", "date": "2007-04-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2007.ETR083", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2007.ETR083", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr083.pdf", "url": "https://authors.library.caltech.edu/records/kzd49-t8346/files/etr083.pdf" }, "pub_year": "2007", "author_list": "Bohassian, Vasken; Jiang, Anxiao (Andrew); et el." }, { "id": "https://authors.library.caltech.edu/records/9y5yh-y1f10", "eprint_id": 26111, "eprint_status": "archive", "datestamp": "2023-08-19 19:59:30", "lastmod": "2023-10-24 16:14:26", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Bohossian-V", "name": { "family": "Bohossian", "given": "Vasken" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Floating Codes for Joint Information Storage in Write Asymmetric Memories", "ispublished": "unpub", "full_text_status": "public", "note": "This work was supported in part by the Lee Center for Advanced Networking at the California Institute of Technology. \n\nAvailable online: http://www.paradise.caltech.edu/papers/etr080.pdf", "abstract": "Memories whose storage cells transit irreversibly between states have been common since the start of the data storage technology. In recent years, flash memories and other non-volatile memories based on floating-gate cells have become a very important family of such memories. We model them by the Write Asymmetric Memory (WAM), a memory where each cell is in one of q states \u2013 state 0, 1, ... , q-1 \u2013 and can only transit from a lower state to a higher state. Data stored in a WAM can be rewritten by shifting the cells to higher states. Since the state transition is irreversible, the number of times of rewriting is limited. When multiple variables are stored in a WAM, we study codes, which we call floating codes, that maximize the total number of times the variables can be written and rewritten. \n\nIn this paper, we present several families of floating codes\nthat either are optimal, or approach optimality as the codes get longer. We also present bounds to the performance of general floating codes. The results show that floating codes can integrate the rewriting capabilities of different variables to a surprisingly high degree.", "date": "2007-04-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2007.ETR080", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2007.ETR080", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr080.pdf", "url": "https://authors.library.caltech.edu/records/9y5yh-y1f10/files/etr080.pdf" }, "pub_year": "2007", "author_list": "Jiang, Anxiao (Andrew); Bohossian, Vasken; et el." }, { "id": "https://authors.library.caltech.edu/records/y1jv5-er092", "eprint_id": 26110, "eprint_status": "archive", "datestamp": "2023-08-19 19:55:59", "lastmod": "2023-10-24 16:14:24", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Cassuto-Y", "name": { "family": "Cassuto", "given": "Yuval" }, "orcid": "0000-0001-6369-6699" }, { "id": "Schwartz-Moshe", "name": { "family": "Schwartz", "given": "Moshe" }, "orcid": "0000-0002-1449-0026" }, { "id": "Bohassian-V", "name": { "family": "Bohassian", "given": "Vasken" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Codes for Multi-Level Flash Memories: Correcting Asymmetric Limited-Magnitude Errors", "ispublished": "unpub", "full_text_status": "public", "note": "This work was supported in part by the Caltech Lee Center for Advanced Networking. \n\nAvailable online: http://www.paradise.caltech.edu/papers/etr079.pdf", "abstract": "Several physical effects that limit the reliability and performance of Multilevel Flash memories induce errors that have low magnitude and are dominantly asymmetric. This paper studies block codes for asymmetric limited-magnitude errors over q-ary channels. We propose code constructions for such channels when the number of errors is bounded by t. The construction uses known codes for symmetric errors over small alphabets to protect large-alphabet symbols from asymmetric limited-magnitude errors. The encoding and decoding of these codes are performed over the small alphabet whose size depends only on the maximum error magnitude and is independent of the alphabet size of the outer code. An extension of the construction is proposed to include systematic codes as a benet to practical implementation.", "date": "2007-04", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2007.ETR079", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2007.ETR079", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr079.pdf", "url": "https://authors.library.caltech.edu/records/y1jv5-er092/files/etr079.pdf" }, "pub_year": "2007", "author_list": "Cassuto, Yuval; Schwartz, Moshe; et el." }, { "id": "https://authors.library.caltech.edu/records/ecxjb-m2n07", "eprint_id": 26112, "eprint_status": "archive", "datestamp": "2023-08-19 19:56:04", "lastmod": "2023-10-24 16:14:29", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Schwartz-Moshe", "name": { "family": "Schwartz", "given": "Moshe" }, "orcid": "0000-0002-1449-0026" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Constrained Codes as Networks of Relations", "ispublished": "unpub", "full_text_status": "public", "note": "This work was supported in part by the Caltech Lee Center for Advanced Networking. \n\nAlso available from http://www.paradise.caltech.edu/papers/etr082.pdf", "abstract": "We revisit the well-known problem of determining the capacity of constrained systems. While the one-dimensional case is well understood, the capacity of two-dimensional systems is mostly unknown. When it is non-zero, except for the (1,1)-RLL system on the hexagonal lattice, there are no closed-form analytical solutions known. Furthermore, for the related problem of counting the exact number of constrained arrays of any given size, only exponential-time algorithms are known. \n\nWe present a novel approach to finding the exact capacity\nof two-dimensional constrained systems, as well as efficiently counting the exact number of constrained arrays of any given size. To that end, we borrow graph-theoretic tools originally developed for the field of statistical mechanics, tools for efficiently simulating quantum circuits, as well as tools from the theory of the spectral distribution of Toeplitz matrices.", "date": "2007-04", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2007.ETR082", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2007.ETR082", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr082.pdf", "url": "https://authors.library.caltech.edu/records/ecxjb-m2n07/files/etr082.pdf" }, "pub_year": "2007", "author_list": "Schwartz, Moshe and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/hr87k-7y455", "eprint_id": 26117, "eprint_status": "archive", "datestamp": "2023-08-19 19:56:08", "lastmod": "2023-10-24 16:14:37", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Fett-B", "name": { "family": "Fett", "given": "Brian" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" }, { "id": "Riedel-M-D", "name": { "family": "Riedel", "given": "Marc D." }, "orcid": "0000-0002-3318-346X" } ] }, "title": "Synthesizing Stochasticity in Biochemical Systems", "ispublished": "unpub", "full_text_status": "public", "keywords": "Synthetic biology, Computational Biology, Synthesis, Biochemical Reactions, Stochasticity, Markov processes, Random processes", "note": "This work is supported in part by the \"Alpha Project\" at the Center for Genomic Experimentation and Computation, an NIH Center of Excellence (grant no. P50 HG02370). \n\nAlso available from http://www.paradise.caltech.edu/papers/etr081.pdf", "abstract": "Randomness is inherent to biochemistry: at each instant, the sequence of reactions that fires is a matter of chance. Some biological systems exploit such randomness, choosing between different outcomes stochastically \u2013 in effect, hedging their bets with a portfolio of responses for different environmental conditions. In this paper, we discuss techniques for synthesizing such stochastic behavior in engineered biochemical systems. We propose a general method for designing a set of biochemical reactions that produces different combinations of molecular types according to a specified probability distribution. The response is precise and robust to perturbations. Furthermore, it is programmable: the probability distribution is a function of the quantities of input types. The method is modular and extensible. We discuss strategies for implementing various functional dependencies: linear, logarithmic, exponential, etc. This work has potential applications in domains such as biochemical sensing, drug production, and disease treatment. Moreover, it provides a framework for analyzing and characterizing the stochastic dynamics in natural biochemical systems such as the lysis/lysogeny switch of the lambda bacteriophage.", "date": "2007-04", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2007.ETR081", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2007.ETR081", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "DAC07_The_Synthesis_of_Stochasticity_in_Biochemical_Systems_ETR81.pdf", "url": "https://authors.library.caltech.edu/records/hr87k-7y455/files/DAC07_The_Synthesis_of_Stochasticity_in_Biochemical_Systems_ETR81.pdf" }, "pub_year": "2007", "author_list": "Fett, Brian; Bruck, Jehoshua; et el." }, { "id": "https://authors.library.caltech.edu/records/vmf0k-77n02", "eprint_id": 26109, "eprint_status": "archive", "datestamp": "2023-08-19 19:26:46", "lastmod": "2023-10-24 16:14:22", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Schwartz-Moshe", "name": { "family": "Schwartz", "given": "Moshe" }, "orcid": "0000-0002-1449-0026" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Increasing the Information Density of Storage Systems Using the Precision-Resolution Paradigm", "ispublished": "unpub", "full_text_status": "public", "keywords": "run-length limited, constrained coding, capacity of constrained channels", "note": "This work was supported in part by the Caltech Lee Center for Advanced Networking and by NSF grant ANI-0322475. \n\nAvailable online: http://www.paradise.caltech.edu/papers/etr078bis.pdf", "abstract": "Arguably, the most prominent constrained system in storage applications is the (d, k)-RLL (Run-Length Limited) system, where every binary sequence obeys the constraint that every two adjacent 1's are separated by at least d consecutive 0's and at most k consecutive 0's, namely, runs of 0's are length limited. The motivation for the RLL constraint arises mainly from the physical limitations of the read and write technologies in magnetic and optical storage systems. \n\nWe revisit the rationale for the RLL system and reevaluate its relationship to the physical media. As a result, we introduce a new paradigm that better matches the physical constraints. We call the new paradigm the Precision-Resolution (PR) system, where the write operation is limited by precision and the read operation is limited by resolution. \n\nWe compute the capacity of a general PR system and demonstrate that it provides a significant increase in the information density compared to the traditional RLL system (for identical physical limitations). For example, the capacity of the (2, 10)-RLL used in CD-ROMs and DVDs is approximately 0.5418, while our PR system provides the capacity of about 0.7725, resulting in a potential increase of about 40% in information density.", "date": "2007-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2007.ETR078", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2007.ETR078", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr078bis.pdf", "url": "https://authors.library.caltech.edu/records/vmf0k-77n02/files/etr078bis.pdf" }, "pub_year": "2007", "author_list": "Schwartz, Moshe and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/tzg9b-d6z05", "eprint_id": 26108, "eprint_status": "archive", "datestamp": "2023-08-19 19:07:45", "lastmod": "2023-10-24 16:14:20", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Riedel-M-D", "name": { "family": "Riedel", "given": "Marc D." }, "orcid": "0000-0002-3318-346X" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Exact Stochastic Simulation of Chemical Reactions with Cycle Leaping", "ispublished": "unpub", "full_text_status": "public", "note": "This work is supported by the \"Alpha Project\" at the Center for Genomic Experimentation and Computation, a National Institutes of Health Center of Excellence in Genomic Sciences (grant no. P50 HG02370). \n\nAlso available online: http://www.paradise.caltech.edu/papers/etr077.pdf", "abstract": "The stochastic simulation algorithm (SSA), first proposed by Gillespie, has become the workhorse of computational biology. It tracks integer quantities of the molecular species, executing reactions at random based on propensity calculations. An estimate for the resulting quantities of the different species is obtained by averaging the results of repeated trials. Unfortunately, for models with many reaction channels and many species, the algorithm requires a prohibitive amount of computation time. Many trials must be performed, each forming a lengthy trajectory through the state space. With coupled or reversible reactions, the simulation often loops through the same sequence of states repeatedly, consuming computing time, but making no forward progress. \n\nWe propose a algorithm that reduces the simulation time through cycle leaping: when cycles are encountered, the exit probabilities are calculated. Then, in a single bound, the simulation leaps directly to one of the exit states. The technique is exact, sampling the state space with the expected probability distribution. It is a component of a general framework that we have developed for stochastic simulation based on probabilistic analysis and caching.", "date": "2006-12-22", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2006.ETR077", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2006.ETR077", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr077.pdf", "url": "https://authors.library.caltech.edu/records/tzg9b-d6z05/files/etr077.pdf" }, "pub_year": "2006", "author_list": "Riedel, Marc D. and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/getc1-s1714", "eprint_id": 26107, "eprint_status": "archive", "datestamp": "2023-08-19 17:53:18", "lastmod": "2023-10-24 16:14:18", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Cassuto-Y", "name": { "family": "Cassuto", "given": "Yuval" }, "orcid": "0000-0001-6369-6699" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Cyclic Low-Density MDS Array Codes", "ispublished": "unpub", "full_text_status": "public", "abstract": "We construct two infinite families of low density MDS array codes which are also cyclic. One of these families includes the first such sub-family with redundancy parameter r > 2. The two constructions have different algebraic formulations, though they both have the same indirect structure. First MDS codes that are not cyclic are constructed and then by applying a certain mapping to their parity check matrices, non-equivalent cyclic codes with the same distance and density properties are obtained. Using the same proof techniques, a third infinite family of quasi-cyclic codes can be constructed.", "date": "2006-05-30", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2006.ETR076", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2006.ETR076", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr076.pdf", "url": "https://authors.library.caltech.edu/records/getc1-s1714/files/etr076.pdf" }, "pub_year": "2006", "author_list": "Cassuto, Yuval and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/a320x-97y71", "eprint_id": 26106, "eprint_status": "archive", "datestamp": "2023-08-19 17:52:27", "lastmod": "2023-10-24 16:14:16", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Bohossian-V", "name": { "family": "Bohossian", "given": "Vasken" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Shortening Array Codes and the Perfect 1-Factorization Conjecture", "ispublished": "unpub", "full_text_status": "public", "abstract": "The existence of a perfect 1-factorization of the complete graph Kn, for arbitrary n, is a 40-year old open problem in graph theory. Two infinite families of perfect 1-factorizations are known for K2p and Kp+1, where p is a prime. It was shown in [8] that finding a perfect 1-factorization of Kn can be reduced to a problem in coding, i.e. to constructing an MDS, lowest density array code of length n. In this paper, a new method for shortening arbitrary array codes is introduced. It is then used to derive the Kp+1 family of perfect 1-factorizations from the K2p family, by applying the reduction metioned above. Namely, techniques from coding theory are used to prove a new result in graph theory.", "date": "2006-05-24", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2006.ETR075", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2006.ETR075", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr075.pdf", "url": "https://authors.library.caltech.edu/records/a320x-97y71/files/etr075.pdf" }, "pub_year": "2006", "author_list": "Bohossian, Vasken and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/aykkf-taw59", "eprint_id": 26105, "eprint_status": "archive", "datestamp": "2023-08-19 17:33:58", "lastmod": "2023-10-24 16:14:14", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Langberg-M", "name": { "family": "Langberg", "given": "Michael" }, "orcid": "0000-0002-7470-0718" }, { "id": "Sprintson-A", "name": { "family": "Sprintson", "given": "Alexander" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Network Coding: A Computational Perspective", "ispublished": "unpub", "full_text_status": "public", "note": "Research supported in part by by the Caltech Lee Center for Advanced Networking and by NSF grants ANI-0322475 and CCF-0346991. \n\nAlso available from http://www.paradise.caltech.edu/papers/etr072.pdf", "abstract": "In this work, we study the computational perspective of network coding, focusing on two issues. First, we address the computational complexity of finding a network code for acyclic multicast networks. Second, we address the issue of reducing the amount of computation performed by network nodes. In particular, we consider the problem of finding a network code with the minimum possible number of encoding nodes, i.e., nodes that generate new packets by combining the packets received over incoming links. \n\nWe present a deterministic algorithm that finds a feasible network code for a multicast network over an underlying graph G(V,E) in time O(|E|kh + |V |k2h2 + h4k3(k + h)), where k is the number of destinations and h is the number of packets. Our result improves the best known running time of O(|E|kh+ |V |k2h2(k + h)) of the algorithm due to Jaggi et al. [1] in the typical case of large communication graphs. In addition, our algorithm guarantees that the number of encoding nodes in the obtained network code is bounded by O(h3k2). \n\nNext, we address the problem of finding a network code with the minimum number of encoding nodes in both integer and fractional coding networks. We prove that in the majority of settings this problem is NP-hard. However, we show that if h = O(1), k = O(1), and the underlying communication graph is acyclic, then there exists an algorithm that solves this problem in polynomial time.", "date": "2006-03-26", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2006.ETR074", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2006.ETR074", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr074.pdf", "url": "https://authors.library.caltech.edu/records/aykkf-taw59/files/etr074.pdf" }, "pub_year": "2006", "author_list": "Langberg, Michael; Sprintson, Alexander; et el." }, { "id": "https://authors.library.caltech.edu/records/y8vnv-42698", "eprint_id": 26104, "eprint_status": "archive", "datestamp": "2023-08-19 17:15:49", "lastmod": "2023-10-24 16:14:12", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Schwartz-Moshe", "name": { "family": "Schwartz", "given": "Moshe" }, "orcid": "0000-0002-1449-0026" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "On the Capacity of Precision-Resolution Constrained Systems", "ispublished": "unpub", "full_text_status": "public", "note": "This work was supported in part by the Caltech Lee Center for Advanced Networking and by NSF grant ANI-0322475.\n\nAlso available online: http://www.paradise.caltech.edu/papers/etr073.pdf", "abstract": "Arguably, the most famous constrained system is the (d, k)-RLL (Run-Length Limited), in which a stream of bits obeys the constraint that every two 1's are separated by at least d 0's, and there are no more than k consecutive 0's anywhere in the stream. The motivation for this scheme comes from the fact that certain sensor characteristics restrict the minimum time between adjacent 1's or else the two will be merged in the receiver, while a clock drift between transmitter and receiver may cause spurious 0's or missing 0's at the receiver if too many appear consecutively. \n\nThe interval-modulation scheme introduced by Mukhtar and Bruck extends the RLL constraint and implicitly suggests a way of taking advantage of higher-precision clocks. Their work however, deals only with an encoder/decoder construction. \n\nIn this work we introduce a more general framework which we call the precision-resolution (PR) constrained system. In PR systems, the encoder has precision constraints, while the decoder has resolution constraints. We examine the capacity of PR systems and show the gain in the presence of a high-precision encoder (thus, we place the PR system with integral encoder, (p=1,alpha,theta)-PR, which turns out to be a simple extension of RLL, and the PR system with infinite-precision encoder, (infinity,alpha,theta)-PR, on two ends of a continuum). We derive an exact expression for their capacity in terms of the precision p, the minimal resolvable measurement at the decoder alpha, and the decoder resolution factor theta. In an analogy to the RLL terminology these are the clock precision, the minimal time between peaks, and the clock drift. Surprisingly, even with an infinite-precision encoder, the capacity is finite.", "date": "2006-01-31", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2006.ETR073", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2006.ETR073", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr073.pdf", "url": "https://authors.library.caltech.edu/records/y8vnv-42698/files/etr073.pdf" }, "pub_year": "2006", "author_list": "Schwartz, Moshe and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/cvg8d-d9d25", "eprint_id": 26103, "eprint_status": "archive", "datestamp": "2023-08-19 17:13:09", "lastmod": "2023-10-24 16:14:10", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" }, { "id": "Gao-J", "name": { "family": "Gao", "given": "Jie" } }, { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } } ] }, "title": "Adaptive Bloom filter", "ispublished": "unpub", "full_text_status": "public", "keywords": "Bloom Filter, Membership Query, Combinatorics", "abstract": "A Bloom filter is a simple randomized data structure that answers membership query with no false negative and a small false positive probability. It is an elegant data compression technique for membership information, and has broad applications. In this paper, we generalize the traditional Bloom filter to Adaptive Bloom Filter, which incorporates the information on the query frequencies and the membership likelihood of the elements into its optimal design. It has been widely observed that in many applications, some popular elements are queried much more often than the others. The traditional Bloom filter for data sets with irregular query patterns and non-uniform membership likelihood can be further optimized. We derive the optimal configuration of the Bloom filter with query-frequency and membership-likelihood information, and show that the adapted Bloom filter always outperforms the traditional Bloom filter. Under reasonable frequency models such as the step distribution or the Zipf's distribution, the improvement of the false positive probability of the adaptive Bloom filter over that of the traditional Bloom filter is usually of orders of magnitude.", "date": "2006-01-06", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2006.ETR072", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2006.ETR072", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr072.pdf", "url": "https://authors.library.caltech.edu/records/cvg8d-d9d25/files/etr072.pdf" }, "pub_year": "2006", "author_list": "Bruck, Jehoshua; Gao, Jie; et el." }, { "id": "https://authors.library.caltech.edu/records/qmrfh-vb932", "eprint_id": 26102, "eprint_status": "archive", "datestamp": "2023-08-19 16:39:10", "lastmod": "2023-10-24 16:14:07", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Cook-M", "name": { "family": "Cook", "given": "Matthew" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Networks of Relations for Representation, Learning, and Generalization", "ispublished": "unpub", "full_text_status": "public", "abstract": "We propose representing knowledge as a network of relations. Each relation relates only a few continuous or discrete variables, so that any overall relationship among the many variables treated by the network winds up being distributed throughout the network. Each relation encodes which combinations of values correspond to past experience for the variables related by the relation. Variables may or may not correspond to understandable aspects of the situation being modeled by the network. A distributed calculational process can be used to access the information stored in such a network, allowing the network to function as an associative memory. This process in its simplest form is purely inhibitory, narrowing down the space of possibilities as much as possible given the data to be matched. In contrast with methods that always retrieve a best fit for all variables, this method can return values for inferred variables while leaving non-inferable variables in an unknown or partially known state. In contrast with belief propagation methods, this method can be proven to converge quickly and uniformly for any network topology, allowing networks to be as interconnected as the relationships warrant, with no independence assumptions required. The generalization properties of such a memory are aligned with the network's relational representation of how the various aspects of the modeled situation are related.", "date": "2005-11-11", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2005.ETR071", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2005.ETR071", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr071.pdf", "url": "https://authors.library.caltech.edu/records/qmrfh-vb932/files/etr071.pdf" }, "pub_year": "2005", "author_list": "Cook, Matthew and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/7wa2a-91w72", "eprint_id": 26101, "eprint_status": "archive", "datestamp": "2023-08-19 16:06:35", "lastmod": "2023-10-24 16:14:05", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Codenotti-P", "name": { "family": "Codenotti", "given": "Paolo" } }, { "id": "Sprintson-A", "name": { "family": "Sprintson", "given": "Alexander" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Anti-Jamming Schedules for Wireless Broadcast Systems", "ispublished": "unpub", "full_text_status": "public", "abstract": "Modern society is heavily dependent on wireless networks for providing voice and data communications. Wireless data broadcast has recently emerged as an attractive way to disseminate data to a large number of clients. In data broadcast systems, the server proactively transmits the information on a downlink channel; the clients access the data by listening to the channel. Wireless data broadcast systems can serve a large number of heterogeneous clients, minimizing power consumption as well as protecting the privacy of the clients' locations. \n\nThe availability and relatively low cost of antennas resulted in a number of potential threats to the integrity of the wireless infrastructure. The existing solutions and schedules for wireless data broadcast are vulnerable to jamming, i.e., the use of active signals to prevent data distribution. The goal of jammers is to disrupt the normal operation of the broadcast system, which results in high waiting time and excessive power consumption for the clients. \n\nIn this paper we investigate efficient schedules for wireless data broadcast that perform well in the presence of a jammer. We show that the waiting time of client can be efficiently reduced by adding redundancy to the schedule. The main challenge in the design of redundant broadcast schedules is to ensure that the transmitted information is always up-to-date. Accordingly, we present schedules that guarantee low waiting time and low staleness of data in the presence of a jammer. We prove that our schedules are optimal if the jamming signal has certain energy limitations.", "date": "2005-07-20", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2005.ETR070", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2005.ETR070", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr070.pdf", "url": "https://authors.library.caltech.edu/records/7wa2a-91w72/files/etr070.pdf" }, "pub_year": "2005", "author_list": "Codenotti, Paolo; Sprintson, Alexander; et el." }, { "id": "https://authors.library.caltech.edu/records/1cvf7-kcc88", "eprint_id": 26100, "eprint_status": "archive", "datestamp": "2023-08-22 03:54:01", "lastmod": "2023-10-24 16:14:03", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" }, { "id": "Gao-Jie", "name": { "family": "Gao", "given": "Jie" } }, { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } } ] }, "title": "MAP: Medial Axis Based Geometric Routing in Sensor Networks", "ispublished": "unpub", "full_text_status": "public", "keywords": "C.2.2 [Computer Systems Organization]: Computer-Communication Networks\u2013Network Protocols; E.1 [Data]: Data Structures\u2013graphs and networks; Algorithms; Design; Medial Axis; Routing; System Design; Sensor networks", "note": "This work was supported in part by the Lee Center for Advanced Networking at the California Institute of Technology, and by NSF grant CCR-TC-0209042.\n\nSubmitted - etr069.pdf
", "abstract": "One of the challenging tasks in the deployment of dense wireless networks (like sensor networks) is in devising a routing scheme for node to node communication. Important consideration includes scalability, routing complexity, the length of the communication paths and the load sharing of the routes. In this paper, we show that a compact and expressive abstraction of network connectivity by the medial axis enables efficient and localized routing. We propose MAP, a Medial Axis based naming and routing Protocol that does not require locations, makes routing decisions locally, and achieves good load balancing. In its preprocessing phase, MAP constructs the medial axis of the sensor field, defined as the set of nodes with at least two closest boundary nodes. The medial axis of the network captures both the complex geometry and non-trivial topology of the sensor field. It can be represented compactly by a graph whose size is comparable with the complexity of the geometric features (e.g., the number of holes). Each node is then given a name related to its position with respect to the medial axis. The routing scheme is derived through local decisions based on the names of the source and destination nodes and guarantees delivery with reasonable and natural routes. We show by both theoretical analysis and simulations that our medial axis based geometric routing scheme is scalable, produces short routes, achieves excellent load balancing, and is very robust to variations in the network model.", "date": "2005-07-11", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2005.ETR069", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2005.ETR069", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "funders": { "items": [ { "agency": "Caltech Lee Center for Advanced Networking" }, { "agency": "NSF", "grant_number": "CCR-TC-0209042" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "doi": "10.1145/1080829.1080839", "primary_object": { "basename": "etr069.pdf", "url": "https://authors.library.caltech.edu/records/1cvf7-kcc88/files/etr069.pdf" }, "pub_year": "2005", "author_list": "Bruck, Jehoshua; Gao, Jie; et el." }, { "id": "https://authors.library.caltech.edu/records/8ybfg-bxc46", "eprint_id": 26099, "eprint_status": "archive", "datestamp": "2023-08-22 03:37:34", "lastmod": "2023-10-24 16:14:01", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" }, { "id": "Gao-Jie", "name": { "family": "Gao", "given": "Jie" } }, { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } } ] }, "title": "Localization and Routing in Sensor Networks by Local Angle\n Information", "ispublished": "unpub", "full_text_status": "public", "keywords": "E.1 [Data]: Data Structures\u2013graphs and networks; F.2.2 [Theory of Computation]: analysis of algorithms and problem complexity\u2013non-numerical algorithms and problems; Algorithms, Design, Theory; Sensor networks, Wireless networks, Localization, Geographical routing, Embedding, Planar spanner subgraph", "note": "This work was supported in part by the Lee Center for Advanced Networking at the California Institute of Technology, and by NSF grant CCR-TC-0209042.\n\nhttp://www.paradise.caltech.edu/papers/etr068.pdf\n\nSubmitted - etr068.pdf
", "abstract": "Location information is very useful in the design of sensor network infrastructures. In this paper, we study the anchor-free 2D localization problem by using local angle measurements in a sensor network. We prove that given a unit disk graph and the angles between adjacent edges, it is NP-hard to find a valid embedding in the plane such that neighboring nodes are within distance 1 from each other and non-neighboring nodes are at least distance 1 away. Despite the negative results, however, one can find a planar spanner\nof a unit disk graph by using only local angles. The planar spanner can be used to generate a set of virtual coordinates that enable efficient and local routing schemes such as geographical routing or approximate shortest path routing. We also proposed a practical anchor-free embedding scheme by solving a linear program. We show by simulation that not only does it give very good local embedding, i.e., neighboring nodes are close and non-neighboring nodes are far away, but it also gives a quite accurate global view\nsuch that geographical routing and approximate shortest path routing on the embedded graph are almost identical to those on the original (true) embedding. The embedding algorithm can be adapted to other models of wireless sensor networks and is robust to measurement noise.", "date": "2005-05-13", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2005.ETR068", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2005.ETR068", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "funders": { "items": [ { "agency": "Caltech Lee Center for Advanced Networking" }, { "agency": "NSF", "grant_number": "CCR-TC-0209042" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "doi": "10.1145/1062689.1062713", "primary_object": { "basename": "etr068.pdf", "url": "https://authors.library.caltech.edu/records/8ybfg-bxc46/files/etr068.pdf" }, "pub_year": "2005", "author_list": "Bruck, Jehoshua; Gao, Jie; et el." }, { "id": "https://authors.library.caltech.edu/records/dg474-54385", "eprint_id": 26094, "eprint_status": "archive", "datestamp": "2023-08-19 15:32:12", "lastmod": "2023-10-24 16:13:50", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Cook-M", "name": { "family": "Cook", "given": "Matthew" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Implementability Among Predicates", "ispublished": "unpub", "full_text_status": "public", "note": "We would like to thank Erik Winfree for helpful discussions. This research was supported in part by the \"Alpha Project\" that is funded by a grant from the National Human Genome Research Institute (Grant No. P50 HG02370).\n\nhttp://www.paradise.caltech.edu/papers/etr067.pdf", "abstract": "Much work has been done to understand when given predicates (relations) on discrete variables can be conjoined to implement other predicates. Indeed, the lattice of \"co-clones\" (sets of predicates closed under conjunction, variable renaming, and existential quantification of variables) has been investigated steadily from the 1960's to the present. Here, we investigate a more general model, where duplicatability of values is not taken for granted. This model is motivated in part by large scale neural models, where duplicating a value is similar in cost to computing a function, and by quantum mechanics, where values cannot be duplicated. Implementations in this case are naturally given by a graph fragment in which vertices are predicates, internal edges are existentially quantified variables, and \"dangling edges\" (edges emanating from a vertex but not yet connected to another vertex) are the free variables of the implemented predicate. We examine questions of implementability among predicates in this scenario, and\nwe present the solution to all implementability problems for single predicates on up to three boolean values. However, we find that a variety of proof methods are required, and the question of implementability indeed becomes undecidable for larger predicates, although this is tricky to prove. We find that most predicates cannot implement the 3-way equality predicate, which reaffirms the view that duplicatability of values should not be assumed a priori.", "date": "2005-03-20", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2005.ETR067", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2005.ETR067", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr067.pdf", "url": "https://authors.library.caltech.edu/records/dg474-54385/files/etr067.pdf" }, "pub_year": "2005", "author_list": "Cook, Matthew and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/mzz80-z1b49", "eprint_id": 26098, "eprint_status": "archive", "datestamp": "2023-08-19 15:20:56", "lastmod": "2023-10-24 16:13:59", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Cronin-C-J", "name": { "family": "Cronin", "given": "Christopher J." } }, { "id": "Mendel-J-E", "name": { "family": "Mendel", "given": "Jane E." } }, { "id": "Mukhtar-S", "name": { "family": "Mukhtar", "given": "Saleem" } }, { "id": "Kim-Y-M", "name": { "family": "Kim", "given": "Young-Mee" } }, { "id": "Stirbl-R-C", "name": { "family": "Stirbl", "given": "Robert C." } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" }, { "id": "Sternberg-P-W", "name": { "family": "Sternberg", "given": "Paul W." }, "orcid": "0000-0002-7699-0173" } ] }, "title": "An automated system for measuring parameters of nematode sinusoidal movement", "ispublished": "unpub", "full_text_status": "public", "note": "Availability of source code \nSource code is available through a GPL at http://wormlab.caltech.edu/publications/download.html\nDocumentation of this software is available as a pdf from\nhttp://wormlab.caltech.edu/publications/download.html\n\nContributions of authors \nSM, JB, JM and PS conceived and designed the original\nautomated system for tracking and movement measurement.\nSM developed a working prototype system and brought in the key algorithms used. CC wrote most of the code in the current release. JM developed the protocol for the plate assay, and devised the dose-response and genetic experiments. RS conceived of applying automated analysis\nof C. elegans movement for toxicology studies, YK performed\nmost of the toxicology experiments. JM, CC, RS and PS analyzed the data. CC, JM, and PS wrote the paper. All authors read and approved the final manuscript. \n\nAcknowledgements \nWe thank X. Xu for suggesting length normalization, Jonathan Shewchuk for Triangle, and anonymous reviewers for many helpful suggestions. Supported by grants from the ONR (S.B.), DARPA (R. S.) and Howard Hughes Medical Institute, with which PWS is an Investigator. \n\nhttp://www.paradise.caltech.edu/papers/etr066.pdf", "abstract": "Background: Nematode sinusoidal movement has been used as a phenotype in many studies of C. elegans development, behavior and physiology. A thorough understanding of the ways in which genes control these aspects of biology depends, in part, on the accuracy of phenotypic analysis. While worms that move poorly are relatively easy to describe, description of hyperactive movement and movement modulation presents more of a challenge. An enhanced capability to analyze all the complexities of nematode movement will thus help our understanding of how genes control behavior.\n\nResults: We have developed a user-friendly system to analyze nematode movement in an automated and quantitative manner. In this system nematodes are automatically recognized and a computer-controlled microscope stage ensures that the nematode is kept within the camera field of view while video images from the camera are stored on videotape. In a second step, the images from the videotapes are processed to recognize the worm and to extract its changing position and posture over time. From this information, a variety of movement parameters are calculated. These parameters include the velocity of the worm's centroid, the velocity of the worm along its track, the extent and frequency of body bending, the amplitude and wavelength of the sinusoidal movement, and the propagation of the contraction wave along the body. The length of the worm is also determined and used to normalize the amplitude and wavelength measurements. \n\nTo demonstrate the utility of this system, we report here a comparison of movement parameters for a small set of mutants\naffecting the Go/Gq mediated signaling network that controls acetylcholine release at the neuromuscular junction. The system allows comparison of distinct genotypes that affect movement similarly (activation of Gq-alpha versus loss of Go-alpha function), as well as of different mutant alleles at a single locus (null and dominant negative alleles of the goa-1 gene, which encodes Goalpha). We also demonstrate the use of this system for analyzing the effects of toxic agents. Concentration-response curves for the toxicants arsenite and aldicarb, both of which affect motility, were determined for wild-type and several mutant strains,\nidentifying P-glycoprotein mutants as not significantly more sensitive to either compound, while cat-4 mutants are more sensitive to arsenite but not aldicarb.\n\nConclusions: Automated analysis of nematode movement facilitates a broad spectrum of experiments. Detailed genetic analysis of multiple alleles and of distinct genes in a regulatory network is now possible. These studies will facilitate quantitative modeling of C. elegans movement, as well as a comparison of gene function. Concentration-response curves will allow rigorous analysis\nof toxic agents as well as of pharmacological agents. This type of system thus represents a powerful analytical tool that can be readily coupled with the molecular genetics of nematodes.", "date": "2005-02-07", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2005.ETR066", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2005.ETR066", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr066.pdf", "url": "https://authors.library.caltech.edu/records/mzz80-z1b49/files/etr066.pdf" }, "pub_year": "2005", "author_list": "Cronin, Christopher J.; Mendel, Jane E.; et el." }, { "id": "https://authors.library.caltech.edu/records/qagwh-p5v35", "eprint_id": 26097, "eprint_status": "archive", "datestamp": "2023-08-19 15:17:30", "lastmod": "2023-10-24 16:13:57", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Monotone Percolation and The Topology Control of Wireless Networks", "ispublished": "unpub", "full_text_status": "public", "keywords": "Combinatorics, Graph theory, Probability, Topology, Topology Control, Wireless network.", "note": "The authors would like to thank Matthew Cook, Jie Gao and Michael Langberg for their helpful discussions, and thank\nthe anonymous reviewers for their helpful comments.\n\nThis work was supported in part by the Lee Center for Advanced Networking at the California Institute of Technology, and by NSF grant CCR-TC-0209042.\n\nhttp://www.paradise.caltech.edu/papers/etr065.pdf", "abstract": "This paper addresses the topology control problem for large wireless networks that are modelled by an infinite point process on a two-dimensional plane. Topology control is the process of determining the edges in the network by adjusting\nthe transmission radii of the nodes. Topology control algorithms should be based on local decisions, be adaptive to changes, guarantee full connectivity and support efficient routing. We present a family of topology control algorithms that, respectively, achieve some or all of these requirements efficiently. The key idea in our algorithms is a concept that we call monotone percolation. In classical percolation theory, we are interested in the emergence of an infinitely large connected component. In contrast, in monotone percolation we are interested in the existence of a relatively short path that makes monotonic progress between any pair of source and destination nodes. Our key contribution is that we demonstrate how local decisions on the transmission radii can lead to monotone percolation and in turn to efficient topology control algorithms.", "date": "2005-01-31", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2005.ETR065", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2005.ETR065", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr065.pdf", "url": "https://authors.library.caltech.edu/records/qagwh-p5v35/files/etr065.pdf" }, "pub_year": "2005", "author_list": "Jiang, Anxiao (Andrew) and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/3t5b3-81t27", "eprint_id": 26096, "eprint_status": "archive", "datestamp": "2023-08-19 15:17:26", "lastmod": "2023-10-24 16:13:54", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Cassuto-Y", "name": { "family": "Cassuto", "given": "Yuval" }, "orcid": "0000-0001-6369-6699" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Network Coding for Nonuniform Demands", "ispublished": "unpub", "full_text_status": "public", "abstract": "In this paper we define nonuniform-demand networks as a useful connection model, in between multicasts and general connections. In these networks, the source has a pool of messages, and each sink demands a certain number of messages, without specifying their identities. We study the solvability of such networks and give a tight bound on the number of sinks that achieve capacity in a worst-case network. We propose constructions to solve networks at, or slightly below capacity, and investigate the effect large alphabets have on the solvability of such networks. We also show that our efficient constructions are suboptimal when used in networks with more sinks, yet this comes with little surprise considering the fact that the general problem is shown to be NP-hard.", "date": "2005-01-31", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2005.ETR064", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2005.ETR064", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr064.pdf", "url": "https://authors.library.caltech.edu/records/3t5b3-81t27/files/etr064.pdf" }, "pub_year": "2005", "author_list": "Cassuto, Yuval and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/1bv0x-ym004", "eprint_id": 26095, "eprint_status": "archive", "datestamp": "2023-08-19 14:38:46", "lastmod": "2023-10-24 16:13:52", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Langberg-M", "name": { "family": "Langberg", "given": "Michael" }, "orcid": "0000-0002-7470-0718" }, { "id": "Sprintson-A", "name": { "family": "Sprintson", "given": "Alexander" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "The Encoding Complexity of Network Coding", "ispublished": "unpub", "full_text_status": "public", "note": "We would like to thank Matthew Cook for useful discussions.\n\nhttp://www.paradise.caltech.edu/papers/etr063.pdf", "abstract": "In the multicast network coding problem, a source s needs to deliver h packets to a set of k terminals over an underlying network G. The nodes of the coding network can be broadly categorized into two groups. The first group includes encoding nodes, i.e., nodes that generate new packets by combining data received from two or more incoming links. The second group includes forwarding nodes that can only duplicate and forward the incoming packets. Encoding nodes are, in general, more expensive due to the need to equip them with encoding capabilities. In addition, encoding nodes incur delay and increase the overall complexity of the network.\n\nAccordingly, in this paper we study the design of multicast coding networks with a limited number of encoding nodes. We prove that in an acyclic coding network, the number of encoding nodes required to achieve the capacity of the network is bounded by h^3k^2. Namely, we present (efficiently constructible) network codes that achieve\ncapacity in which the total number of encoding nodes is independent of the size of the network and is bounded by h^3k^2. We show that the number of encoding nodes may depend both on h and k as we present acyclic instances of the multicast network coding problem in which [Omega](h^2k) encoding nodes are needed.\n\nIn the general case of coding networks with cycles, we show that the number of encoding nodes is limited by the size of the feedback link set, i.e., the minimum number of links that must be removed from the network in order to eliminate cycles. Specifically, we prove that the number of encoding nodes is bounded by (2B+1)h^3k^2, where B is the minimum size of the feedback link set. Finally, we observe that determining or even crudely approximating the minimum number of encoding nodes needed to achieve the capacity for a given instance of the network coding problem is NP-hard.", "date": "2004-11-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2004.ETR063", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2004.ETR063", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr063.pdf", "url": "https://authors.library.caltech.edu/records/1bv0x-ym004/files/etr063.pdf" }, "pub_year": "2004", "author_list": "Langberg, Michael; Sprintson, Alexander; et el." }, { "id": "https://authors.library.caltech.edu/records/aw3am-f5v45", "eprint_id": 26093, "eprint_status": "archive", "datestamp": "2023-08-19 14:28:18", "lastmod": "2023-10-24 16:13:48", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Langberg-M", "name": { "family": "Langberg", "given": "Michael" }, "orcid": "0000-0002-7470-0718" }, { "id": "Sprintson-A", "name": { "family": "Sprintson", "given": "Alexander" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Optimal Schedules for Asynchronous Transmission of Discrete Packets", "ispublished": "unpub", "full_text_status": "public", "abstract": "In this paper we study the distribution of dynamic data over a broadcast channel to a large number of\npassive clients. Clients obtain the information by accessing the channel and listening for the next available\npacket. This scenario, referred to as packet-based or discrete broadcast, has many practical applications such\nas the distribution of weather and traffic updates to wireless mobile devices, reconfiguration and reprogramming\nof wireless sensors and downloading dynamic task information in battlefield networks.\nThe optimal broadcast protocols require a high degree of synchronization between the server and the\nwireless clients. However, in typical wireless settings such degree of synchronization is difficult to achieve\ndue to the inaccuracy of internal clocks. Moreover, in some settings, such as military applications, synchronized\ntransmission is not desirable due to jamming. The lack of synchronization leads to large delays\nand excessive power consumption. Accordingly, in this work we focus on the design of optimal broadcast\nschedules that are robust to clock inaccuracy. We present universal schedules for delivery of up-to-date\ninformation with minimum waiting time in asynchronous settings.", "date": "2004-10-12", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2004.ETR062", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2004.ETR062", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr062.pdf", "url": "https://authors.library.caltech.edu/records/aw3am-f5v45/files/etr062.pdf" }, "pub_year": "2004", "author_list": "Langberg, Michael; Sprintson, Alexander; et el." }, { "id": "https://authors.library.caltech.edu/records/a9g9f-9px19", "eprint_id": 26092, "eprint_status": "archive", "datestamp": "2023-08-19 14:17:48", "lastmod": "2023-10-24 16:13:46", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehosua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Network File Storage With Graceful Performance Degradation", "ispublished": "unpub", "full_text_status": "public", "keywords": "Algorithms, Performance, Reliability, Theory\nDomination, file assignment, interleaving, memory allocation,\nfault tolerance", "abstract": "A file storage scheme is proposed for networks containing heterogeneous clients. In the scheme, the\nperformance measured by file-retrieval delays degrades gracefully under increasingly serious faulty\ncircumstances. The scheme combines coding with storage for better performance. The problem\nis NP-hard for general networks; and this paper focuses on tree networks with asymmetric edges\nbetween adjacent nodes. A polynomial-time memory-allocation algorithm is presented, which\ndetermines how much data to store on each node, with the objective of minimizing the total\namount of data stored in the network. Then a polynomial-time data-interleaving algorithm is used\nto determine which data to store on each node for satisfying the quality-of-service requirements in\nthe scheme. By combining the memory-allocation algorithm with the data-interleaving algorithm,\nan optimal solution to realize the file storage scheme in tree networks is established.", "date": "2004-09-23", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2004.ETR061", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2004.ETR061", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr061.pdf", "url": "https://authors.library.caltech.edu/records/a9g9f-9px19/files/etr061.pdf" }, "pub_year": "2004", "author_list": "Jiang, Anxiao (Andrew) and Bruck, Jehosua" }, { "id": "https://authors.library.caltech.edu/records/0r8dz-xf638", "eprint_id": 26090, "eprint_status": "archive", "datestamp": "2023-08-19 13:37:12", "lastmod": "2023-10-24 16:13:42", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Cassuto-Y", "name": { "family": "Cassuto", "given": "Yuval" }, "orcid": "0000-0001-6369-6699" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "A Combinatorial Bound on the List Size", "ispublished": "unpub", "full_text_status": "public", "abstract": "In this paper we study the scenario in which a server sends dynamic data over a single broadcast channel to\na number of passive clients. We consider the data to consist of discrete packets, where each update is sent in a\nseparate packet. On demand, each client listens to the channel in order to obtain the most recent data packet. Such\nscenarios arise in many practical applications such as the distribution of weather and traffic updates to wireless\nmobile devices and broadcasting stock price information over the Internet.\nTo satisfy a request, a client must listen to at least one packet from beginning to end. We thus consider the design\nof a broadcast schedule which minimizes the time that passes between a clients request and the time that it hears a new data packet, i.e., the waiting time of the client. Previous studies have addressed this objective, assuming that client requests are distributed uniformly over time. However, in the general setting, the clients behavior is difficult to predict and might not be known to the server. In this work we consider the design of universal schedules that guarantee a short waiting time for any possible client behavior. We define the model of dynamic broadcasting in\nthe universal setting, and prove various results regarding the waiting time achievable in this framework.", "date": "2004-05-25", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2004.ETR058", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2004.ETR058", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr058.pdf", "url": "https://authors.library.caltech.edu/records/0r8dz-xf638/files/etr058.pdf" }, "pub_year": "2004", "author_list": "Cassuto, Yuval and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/33zeb-29k56", "eprint_id": 26089, "eprint_status": "archive", "datestamp": "2023-08-19 13:36:25", "lastmod": "2023-10-24 16:13:40", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Riedel-M-D", "name": { "family": "Riedel", "given": "Marc D." }, "orcid": "0000-0002-3318-346X" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Timing Analysis of Cyclic Combinatorial Circuits", "ispublished": "unpub", "full_text_status": "public", "abstract": "The accepted wisdom is that combinational circuits must have acyclic (i.e., loop-free or feed-forward) topologies. And yet simple examples suggest that this need not be so. In previous work, we advocated the design of cyclic combinational circuits (i.e., circuits with loops or feedback paths). We proposed a methodology for analyzing and synthesizing such circuits, with an emphasis on the optimization of area.\n\nIn this paper, we extend our methodology into the temporal realm. We characterize the true delay of cyclic circuits through symbolic event propagation in the floating mode of operation, according to the up-bounded inertial delay model. We present analysis results for circuits optimized with our program CYCLIFY. Some benchmark circuits were optimized significantly, with simultaneous improvements of up to 10% in the area and 25% in the delay.", "date": "2004-05-17", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2004.ETR060.1160", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2004.ETR060.1160", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "PDF_logo.gif", "url": "https://authors.library.caltech.edu/records/33zeb-29k56/files/PDF_logo.gif" }, "related_objects": [ { "basename": "Powerpoint_Logo.gif", "url": "https://authors.library.caltech.edu/records/33zeb-29k56/files/Powerpoint_Logo.gif" }, { "basename": "Timing_Analysis_of_Cyclic_Combinational_Circuits,_Marc_D._Riedel_and_Jehoshua_Bruck,_Caltech.html", "url": "https://authors.library.caltech.edu/records/33zeb-29k56/files/Timing_Analysis_of_Cyclic_Combinational_Circuits,_Marc_D._Riedel_and_Jehoshua_Bruck,_Caltech.html" }, { "basename": "etr060.pdf", "url": "https://authors.library.caltech.edu/records/33zeb-29k56/files/etr060.pdf" }, { "basename": "iwls04.ppt", "url": "https://authors.library.caltech.edu/records/33zeb-29k56/files/iwls04.ppt" } ], "pub_year": "2004", "author_list": "Riedel, Marc D. and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/37q5t-gxg91", "eprint_id": 26091, "eprint_status": "archive", "datestamp": "2023-08-19 13:27:07", "lastmod": "2023-10-24 16:13:44", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Langberg-M", "name": { "family": "Langberg", "given": "Michael" }, "orcid": "0000-0002-7470-0718" }, { "id": "Sprintson-A", "name": { "family": "Sprintson", "given": "Alexander" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Optimal Unviersal Schedules for Discrete Broadcast", "ispublished": "unpub", "full_text_status": "public", "abstract": "In this paper we study the scenario in which a server sends dynamic data over a single broadcast channel to\na number of passive clients. We consider the data to consist of discrete packets, where each update is sent in a\nseparate packet. On demand, each client listens to the channel in order to obtain the most recent data packet. Such\nscenarios arise in many practical applications such as the distribution of weather and traffic updates to wireless\nmobile devices and broadcasting stock price information over the Internet.\nTo satisfy a request, a client must listen to at least one packet from beginning to end. We thus consider the design\nof a broadcast schedule which minimizes the time that passes between a clients request and the time that it hears a\nnew data packet, i.e., the waiting time of the client. Previous studies have addressed this objective, assuming that\nclient requests are distributed uniformly over time. However, in the general setting, the clients behavior is difficult\nto predict and might not be known to the server. In this work we consider the design of universal schedules that\nguarantee a short waiting time for any possible client behavior. We define the model of dynamic broadcasting in\nthe universal setting, and prove various results regarding the waiting time achievable in this framework.", "date": "2004-04-12", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2004.ETR057", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2004.ETR057", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr057.pdf", "url": "https://authors.library.caltech.edu/records/37q5t-gxg91/files/etr057.pdf" }, "pub_year": "2004", "author_list": "Langberg, Michael; Sprintson, Alexander; et el." }, { "id": "https://authors.library.caltech.edu/records/thsck-vr733", "eprint_id": 26088, "eprint_status": "archive", "datestamp": "2023-08-19 12:55:04", "lastmod": "2023-10-24 16:13:37", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Cook-M", "name": { "family": "Cook", "given": "Matthew" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Optimal Interleaving on Tori", "ispublished": "unpub", "full_text_status": "public", "abstract": "We study t-interleaving on two-dimensional tori, which is defined by the property that any connected subgraph with t or fewer vertices in the torus is labelled by all distinct integers. It has applications in distributed data storage and burst error correction, and is closely related to Lee metric codes. We say that a torus can be perfectly t-interleaved if its t-interleaving number \u2013 the minimum number of distinct integers needed to t-interleave the torus \u2013 meets the spherepacking lower bound. We prove the necessary and sufficient conditions for tori that can be perfectly t-interleaved, and present efficient perfect t-interleaving constructions. The most important contribution of this paper is to prove that the t-interleaving numbers of tori large enough in both dimensions, which constitute by far the majority of all existing cases, is at most one more than\nthe sphere-packing lower bound, and to present an optimal and efficient t-interleaving scheme for them. Then we prove some bounds on the t-interleaving numbers for other cases, completing a general picture for the t-interleaving problem on 2-dimensional tori.", "date": "2004-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2004.ETR059", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2004.ETR059", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr059.pdf", "url": "https://authors.library.caltech.edu/records/thsck-vr733/files/etr059.pdf" }, "pub_year": "2004", "author_list": "Jiang, Anxiao (Andrew); Cook, Matthew; et el." }, { "id": "https://authors.library.caltech.edu/records/788gb-dba94", "eprint_id": 26087, "eprint_status": "archive", "datestamp": "2023-08-19 12:54:59", "lastmod": "2023-10-24 16:13:35", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Foltz-K", "name": { "family": "Foltz", "given": "Kevin" } }, { "id": "Xu-L", "name": { "family": "Xu", "given": "Lihao" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Scheduling for Efficient Data Broadcast over Two Channels", "ispublished": "unpub", "full_text_status": "public", "abstract": "The broadcast disk provides a way to distribute data to many clients simultaneously. A central server fixes a set of data and a schedule for sending it, and then repeatedly sends the data according to the schedule. Clients listen for data until it is broadcast. We look at the problem of scheduling for two separate channels, where each can have a different broadcast schedule. Our metric for measuring schedule performance is expected delivery time (EDT), the expected value of the total elapsed time between when a client starts listening for data and when the client is completely finished receiving the data. We fix the first channel with a schedule that is optimal for an average case, and look at how to schedule for the second channel.We show two interesting results for sending two items over two channels. The first is that all schedules with equal portions of the two items in the second channel have the same EDT. The second is that for a situation that is symmetric in the two items the optimal schedule is asymmetric with respect to these items.", "date": "2004-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2004.ETR056", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2004.ETR056", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr056.pdf", "url": "https://authors.library.caltech.edu/records/788gb-dba94/files/etr056.pdf" }, "pub_year": "2004", "author_list": "Foltz, Kevin; Xu, Lihao; et el." }, { "id": "https://authors.library.caltech.edu/records/t4bc1-d9a83", "eprint_id": 26080, "eprint_status": "archive", "datestamp": "2023-08-19 11:20:15", "lastmod": "2023-10-24 16:13:21", "type": "book_section", "metadata_visibility": "show", "creators": { "items": [ { "id": "Jiang-Anxiao-Andrew", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" }, "orcid": "0000-0002-0120-7930" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Optimal Content Placement for En-Route Web Caching", "ispublished": "unpub", "full_text_status": "public", "note": "\u00a9 2003 IEEE.\nIssue Date: 16-18 April 2003.\nDate of Current Version: 28 May 2003.\n\nThis work was supported in part by the Lee Center for Advanced Networking\nat the California Institute of Technology.\n\nSubmitted - etr050.pdf
Submitted - etr050.ps
", "abstract": "This paper studies the optimal placement of web files for en-route web caching. It is shown that existing placement policies are all solving restricted partial problems of the file placement problem, and therefore give only sub-optimal solutions. A dynamic programming algorithm of low complexity which computes the optimal solution is presented. It is shown both analytically and experimentally that the file-placement solution output by our algorithm outperforms existing en-route caching policies. The optimal placement of web files can be implemented with a reasonable level of cache coordination and management overhead for en-route caching; and importantly, it can be achieved with or without using data prefetching.", "date": "2003-04-16", "date_type": "published", "publisher": "IEEE", "place_of_pub": "Los Alamitos, CA", "pagerange": "9-16", "id_number": "CaltechPARADISE:ETR050", "isbn": "0-7695-1938-5", "book_title": "Second IEEE International Symposium on Network Computing and Applications", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:ETR050", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "funders": { "items": [ { "agency": "Caltech Lee Center for Advanced Networking" } ] }, "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "doi": "10.1109/NCA.2003.1201132", "primary_object": { "basename": "etr050.pdf", "url": "https://authors.library.caltech.edu/records/t4bc1-d9a83/files/etr050.pdf" }, "related_objects": [ { "basename": "etr050.ps", "url": "https://authors.library.caltech.edu/records/t4bc1-d9a83/files/etr050.ps" } ], "pub_year": "2003", "author_list": "Jiang, Anxiao (Andrew) and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/j22pr-2a704", "eprint_id": 26083, "eprint_status": "archive", "datestamp": "2023-08-19 10:46:56", "lastmod": "2023-10-24 16:13:27", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Riedel-M-D", "name": { "family": "Riedel", "given": "Marc D." }, "orcid": "0000-0002-3318-346X" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Algorithmic Aspects of Cyclic Combinational Circuit Synthesis", "ispublished": "unpub", "full_text_status": "public", "abstract": "Digital circuits are called combinational if they are memoryless: if they have outputs that depend only on the current values of the inputs. Combinational circuits are generally thought of as acyclic (i.e., feed-forward) structures. And yet, cyclic circuits can be combinational. Cycles sometimes occur in designs synthesized from high-level descriptions, as well as in bus-based designs [16]. Feedback in such cases is carefully contrived, typically occurring when functional units are connected in a cyclic topology. Although the premise of cycles in combinational circuits has been accepted, and analysis techniques have been proposed [7], no one has attempted the synthesis of circuits with feedback at the logic level.\n\nWe have argued the case for a paradigm shift in combinational circuit design [10]. We should no longer think of combinational logic as acyclic in theory or in practice, since most combinational circuits are best designed with cycles. We have proposed a general methodology for the synthesis of multilevel networks with cyclic topologies and incorporated it in a general logic synthesis environment. In trials, benchmark circuits were optimized significantly, with improvements of up to 30%I n the area. In this paper, we discuss algorithmic aspects of cyclic circuit design. We formulate a symbolic framework for analysis based on a divide-and-conquer strategy. Unlike previous approaches, our method does not require ternary-valued simulation. Our analysis for combinationality is tightly coupled with the synthesis phase, in which we assemble a combinational network from smaller combinational components. We discuss the underpinnings of the heuristic search methods and present examples as well as synthesis results for benchmark circuits.\n\nIn this paper, we discuss algorithmic aspects of cyclic circuit design. We formulate a symbolic framework for analysis based on a divide-and-conquer strategy. Unlike previous approaches, our method does not require ternary-valued simulation. Our analysis for combinationality is tightly coupled with the synthesis phase, in which we assemble a combinational network from smaller combinational components. We discuss the underpinnings of the heuristic search methods and present examples as well as synthesis results for benchmark circuits.", "date": "2003-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:ETR053", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:ETR053", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr053.pdf", "url": "https://authors.library.caltech.edu/records/j22pr-2a704/files/etr053.pdf" }, "related_objects": [ { "basename": "etr053.ps", "url": "https://authors.library.caltech.edu/records/j22pr-2a704/files/etr053.ps" } ], "pub_year": "2003", "author_list": "Riedel, Marc D. and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/9814j-0a422", "eprint_id": 26085, "eprint_status": "archive", "datestamp": "2023-08-19 10:47:05", "lastmod": "2023-10-24 16:13:31", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Slivkins-A", "name": { "family": "Slivkins", "given": "Aleksandrs" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Interleaving Schemes on Circulant Graphs with Two Offsets", "ispublished": "unpub", "full_text_status": "public", "abstract": "To be added.", "date": "2003-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2003.ETR054", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2003.ETR054", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr054.pdf", "url": "https://authors.library.caltech.edu/records/9814j-0a422/files/etr054.pdf" }, "pub_year": "2003", "author_list": "Slivkins, Aleksandrs and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/0prc7-09k21", "eprint_id": 26081, "eprint_status": "archive", "datestamp": "2023-08-19 10:46:43", "lastmod": "2023-10-24 16:13:23", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" }, { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } } ] }, "title": "Multi-Cluster interleaving in linear arrays and rings", "ispublished": "unpub", "full_text_status": "public", "abstract": "Interleaving codewords is an important method not only for combatting burst-errors, but also for flexible data-retrieving. This paper defines the Multi-Cluster Interleaving (MCI) problem, an interleaving problem for parallel data-retrieving. The MCI problems on linear arrays and rings are studied. The following problem is completely solved: how to interleave integers on a linear array or ring such that any m (m greater than or equal to 2) non-overlapping segments of length 2 in the array or ring have at least 3 distinct integers. We then present a scheme using a 'hierarchical-chain structure' to solve the following more general problem for linear arrays: how to interleave integers on a linear array such that any m (m greater than or equal to 2) non-overlapping segments of length L (L greater than or equal to 2) in the array have at least L + 1 distinct integers. It is shown that the scheme using the 'hierarchical-chain structure' solves the second interleaving problem for arrays that are asymptotically as long as the longest array on which an MCI exists, and clearly, for shorter arrays as well.", "date": "2003-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2003.ETR051", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2003.ETR051", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr051.pdf", "url": "https://authors.library.caltech.edu/records/0prc7-09k21/files/etr051.pdf" }, "related_objects": [ { "basename": "etr051.ps", "url": "https://authors.library.caltech.edu/records/0prc7-09k21/files/etr051.ps" } ], "pub_year": "2003", "author_list": "Bruck, Jehoshua and Jiang, Anxiao (Andrew)" }, { "id": "https://authors.library.caltech.edu/records/azx95-b8232", "eprint_id": 26086, "eprint_status": "archive", "datestamp": "2023-08-19 10:47:10", "lastmod": "2023-10-24 16:13:33", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Franceschetti-M", "name": { "family": "Franceschetti", "given": "Massimo" } }, { "id": "Booth-L", "name": { "family": "Booth", "given": "Lorna" } }, { "id": "Cook-M", "name": { "family": "Cook", "given": "Matthew" } }, { "id": "Meester-R", "name": { "family": "Meester", "given": "Ronald" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Percolation in Multi-hop Wireless Networks", "ispublished": "unpub", "full_text_status": "public", "abstract": "To be added", "date": "2003-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2003.ETR055", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2003.ETR055", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr055.pdf", "url": "https://authors.library.caltech.edu/records/azx95-b8232/files/etr055.pdf" }, "pub_year": "2003", "author_list": "Franceschetti, Massimo; Booth, Lorna; et el." }, { "id": "https://authors.library.caltech.edu/records/cy22z-4f190", "eprint_id": 26084, "eprint_status": "archive", "datestamp": "2023-08-19 10:47:00", "lastmod": "2023-10-24 16:13:29", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Riedel-Marc-D", "name": { "family": "Riedel", "given": "Marc D." }, "orcid": "0000-0002-3318-346X" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "The Synthesis of Cyclic Combinatorial Circuits", "ispublished": "unpub", "full_text_status": "public", "abstract": "To be added.", "date": "2003-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:ETR052a", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:ETR052a", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr052revised.pdf", "url": "https://authors.library.caltech.edu/records/cy22z-4f190/files/etr052revised.pdf" }, "pub_year": "2003", "author_list": "Riedel, Marc D. and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/gc4vq-v3988", "eprint_id": 26082, "eprint_status": "archive", "datestamp": "2023-08-19 10:46:50", "lastmod": "2023-10-24 16:13:25", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Riedel-M-D", "name": { "family": "Riedel", "given": "Marc D." }, "orcid": "0000-0002-3318-346X" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "The Synthesis of Cyclic Combinatorial Circuits", "ispublished": "unpub", "full_text_status": "public", "abstract": "To be added.", "date": "2003-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:ETR052", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:ETR052", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr052.pdf", "url": "https://authors.library.caltech.edu/records/gc4vq-v3988/files/etr052.pdf" }, "related_objects": [ { "basename": "etr052.ps", "url": "https://authors.library.caltech.edu/records/gc4vq-v3988/files/etr052.ps" } ], "pub_year": "2003", "author_list": "Riedel, Marc D. and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/y075m-mfm96", "eprint_id": 26072, "eprint_status": "archive", "datestamp": "2023-08-20 03:49:33", "lastmod": "2023-10-24 16:13:05", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" }, { "id": "Dolev-D", "name": { "family": "Dolev", "given": "Danny" } }, { "id": "Ho-Ching-Tien", "name": { "family": "Ho", "given": "Ching-Tien" } }, { "id": "Ro\u015fu-M-C", "name": { "family": "Ro\u015fu", "given": "Marcel-C\u0103t\u0103lin" } }, { "id": "Strong-R", "name": { "family": "Strong", "given": "Ray" } } ] }, "title": "Efficient Message Passing Interface (MPI) for Parallel Computing on Clusters of Workstations", "ispublished": "unpub", "full_text_status": "public", "note": "Submitted - etr002.pdf
Submitted - etr002.ps
", "abstract": "Parallel computing on clusters of workstations and personal computers has very high\npotential, since it leverages existing hardware and software. Parallel programming \nenvironments offer the user a convenient way to express parallel computation and communication.\nIn fact, recently, a Message Passing Interface (MPI) has been proposed as an industrial\nstandard for writing \"portable\" message-passing parallel programs. The communication\npart of MPI consists of the usual point-to-point communication as well as collective \ncommunication. However, existing implementations of programming environments for clusters\nare built on top of a point-to-point communication layer (send and receive) over local\narea networks (LANs) and, as a result, suffer from poor performance in the collective\ncommunication part.\nIn this paper, we present an efficient design and implementation of the collective \ncommunication part in MPI that is optimized for clusters of workstations. Our system consists\nof two main components: the MPI-CCL layer that includes the collective communication\nfunctionality of MPI and a User-level Reliable Transport Protocol (URTP) that interfaces\nwith the LAN Data-link layer and leverages the fact that the LAN is a broadcast medium.\nOur system is integrated with the operating system via an efficient kernel extension \nmechanism that we developed. The kernel extension significantly improves the performance of\nour implementation as it can handle part of the communication overhead without involving\nuser space.\nWe have implemented our system on a collection of IBM RS/6000 workstations con-\nnected via a lOMbit Ethernet LAN. Our performance measurements are taken from typical\nscientific programs that run in a parallel mode by means of the MPI. The hypothesis behind\nour design is that system's performance will be bounded by interactions between the kernel\nand user space rather than by the bandwidth delivered by the LAN Data-Link Layer. Our\nresults indicate that the performance of our MPI Broadcast (on top of Ethernet) is about\ntwice as fast as a recently published software implementation of broadcast on top of ATM.", "date": "2002-09-04", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1994.ETR002", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1994.ETR002", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "doi": "10.1145/215399.215421", "primary_object": { "basename": "etr002.pdf", "url": "https://authors.library.caltech.edu/records/y075m-mfm96/files/etr002.pdf" }, "related_objects": [ { "basename": "etr002.ps", "url": "https://authors.library.caltech.edu/records/y075m-mfm96/files/etr002.ps" } ], "pub_year": "2002", "author_list": "Bruck, Jehoshua; Dolev, Danny; et el." }, { "id": "https://authors.library.caltech.edu/records/edv6k-qm527", "eprint_id": 26032, "eprint_status": "archive", "datestamp": "2023-08-19 08:53:36", "lastmod": "2023-10-24 16:11:38", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Franceschetti-M", "name": { "family": "Franceschetti", "given": "Massimo" } }, { "id": "Cook-M", "name": { "family": "Cook", "given": "Matthew" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "A Geometric Theorem for Wireless Network Design Optimization", "ispublished": "unpub", "full_text_status": "public", "abstract": "Consider an infinite square grid G. How many\ndiscs of given radius r, centered at the vertices of G, are \nrequired, in the worst case, to completely cover an arbitrary disc of radius r placed on the plane? We show that this number is an integer in the set (3.4; 5.6) whose value depends on the ratio of r to the grid spacing.\nThis result can be applied at the very early design stage of\na wireless cellular network to determine, under the recent\nInternational Telecommunication Union (ITU) proposal for\na traffic load model, and under the assumption that each\nclient is able to communicate if it is within a certain range from a base station, conditions for which a grid network design is cost effective, for any expected traffic demand.", "date": "2002-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2002.ETR044", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2002.ETR044", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr044.pdf", "url": "https://authors.library.caltech.edu/records/edv6k-qm527/files/etr044.pdf" }, "related_objects": [ { "basename": "etr044.ps", "url": "https://authors.library.caltech.edu/records/edv6k-qm527/files/etr044.ps" } ], "pub_year": "2002", "author_list": "Franceschetti, Massimo; Cook, Matthew; et el." }, { "id": "https://authors.library.caltech.edu/records/bhdsr-zxz48", "eprint_id": 26077, "eprint_status": "archive", "datestamp": "2023-08-19 08:54:01", "lastmod": "2023-10-24 16:13:12", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Booth-L", "name": { "family": "Booth", "given": "Lorna" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" }, { "id": "Cook-M", "name": { "family": "Cook", "given": "Matthew" } }, { "id": "Franceschetti-M", "name": { "family": "Franceschetti", "given": "Massimo" } } ] }, "title": "Ad hoc wireless networks with noisy links", "ispublished": "unpub", "full_text_status": "public", "abstract": "Models of ad-hoc wireless networks are often based on the geometric disc abstraction: transmission is assumed to be isotropic, and reliable communication channels are assumed to assumed to exist (apart from interference) between nodes closer than a given distance. In reality communication channels are unreliable and communication range is generally not rotationally symmetric. In this paper we examine how these issues affect network connectivity. Using ideas from percolation theory, we compare networks of geometric discs to other simple shapes, including probabilistic connections, and find that when transmission range and node density are normalized across experiments so as to preserve the expected number of connections (ENC) enjoyed by each node, the discs are the \"hardest\" shape to connect together. In other words, anisotropic radiation patterns and spotty coverage allow an unbounded connected component to appear at lower ENC levels than perfect circular coverage allows. This indicates that connectivity claims made in the literature using the geometric disc abstraction will in general hold also for the more irregular shapes found in practice.", "date": "2002-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2002.ETR047", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2002.ETR047", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr047.pdf", "url": "https://authors.library.caltech.edu/records/bhdsr-zxz48/files/etr047.pdf" }, "related_objects": [ { "basename": "etr047.ps", "url": "https://authors.library.caltech.edu/records/bhdsr-zxz48/files/etr047.ps" } ], "pub_year": "2002", "author_list": "Booth, Lorna; Bruck, Jehoshua; et el." }, { "id": "https://authors.library.caltech.edu/records/18d5j-cqj70", "eprint_id": 26079, "eprint_status": "archive", "datestamp": "2023-08-19 08:54:14", "lastmod": "2023-10-24 16:13:16", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Foltz-K", "name": { "family": "Foltz", "given": "Kevin" } }, { "id": "Xu-L", "name": { "family": "Xu", "given": "Lihao" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Coding and Scheduling for Efficient Loss-Resilient Data Broadcasting", "ispublished": "unpub", "full_text_status": "public", "abstract": "We examine the problem of sending data to clients over a broadcast channel in a way that minimizes the expected waiting time of the clients for this data. This channel, however, is not completely reliable, and packets are occasionally lost. This poses a problem, as performance is greatly degraded by even a single packet loss. For example, one lost packet will increase our expected waiting time for an item from .75 to 2 or 167%, when sending two items with equal demands. We propose and analyze two solutions that attempt to minimize this degradation. In the first, we code packets and in the second we code packets and slightly modify our schedule. The resulting degradations are 67% for the first solution and less than 1% for the second. We conclude that using the second scheme is a very effective way to combat single packet losses, and we extend this solution to combat up to t packet losses per data item for any t [ ] k, where k is the number of packets per data item.", "date": "2002-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2002.ETR049", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2002.ETR049", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "ETR049.pdf", "url": "https://authors.library.caltech.edu/records/18d5j-cqj70/files/ETR049.pdf" }, "related_objects": [ { "basename": "ETR049.ps", "url": "https://authors.library.caltech.edu/records/18d5j-cqj70/files/ETR049.ps" } ], "pub_year": "2002", "author_list": "Foltz, Kevin; Xu, Lihao; et el." }, { "id": "https://authors.library.caltech.edu/records/2jz7r-g7w76", "eprint_id": 26033, "eprint_status": "archive", "datestamp": "2023-08-19 08:53:43", "lastmod": "2023-10-24 16:11:40", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "DNAS: Dispersed Network Attached Storage for Reliability and Performance", "ispublished": "unpub", "full_text_status": "public", "abstract": "NOTE: Text or symbols not renderable in plain ASCII are indicated by [...]. Abstract included in .pdf \n\ndocument.\n\n\nWith the advent of merging between communication and\nstorage, there is an increasing need for developing dis-\ntributed data layout schemes for network attached \nstorage that address reliability and performance challenges.\nThis paper proposes a novel scheme for storing \ninformation on networks. In particular, for a fault-free \noperation, it provides the ability to retrieve data by accessing\nnetwork nodes within a small proximity. In the event of\nfaults, data is guaranteed to be retrieved by exploring a\nslightly larger proximity.\nThe problem of designing layout schemes, namely pro-\nviding Dispersed Network Attached Storage (DNAS), is\nformulated as a graph coloring problem that we call \nLayered Diversity Coloring. Consider the following problem:\ngiven a graph G(V,E) and N colors, how to color vertices\nof G so that every vertex can find at least [...]\n\nIn this paper we study the layered diversity coloring\nproblem where the graph G(V,E) is a tree. A coloring\nalgorithm of time complexity [...] is\npresented, and the sufficient and necessary condition for\nthere to exist a layered diversity coloring on a tree follows\nthe algorithm.", "date": "2002-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2002.ETR043", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2002.ETR043", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr043.pdf", "url": "https://authors.library.caltech.edu/records/2jz7r-g7w76/files/etr043.pdf" }, "related_objects": [ { "basename": "etr043.ps", "url": "https://authors.library.caltech.edu/records/2jz7r-g7w76/files/etr043.ps" } ], "pub_year": "2002", "author_list": "Jiang, Anxiao (Andrew) and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/bak03-gez83", "eprint_id": 26076, "eprint_status": "archive", "datestamp": "2023-08-19 08:53:55", "lastmod": "2023-10-24 16:13:10", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Slivkins-A", "name": { "family": "Slivkins", "given": "Aleksandrs" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Interleaving Schemes on Circulant Graphs", "ispublished": "unpub", "full_text_status": "public", "abstract": "Interleaving schemes are used for error-correcting on a noisy channel. We consider interleaving schemes on infinite circulant graphs with two offsets 1 and d, with a goal to\nminimize the interleaving degree. Our constructions are minimal covers of the graph by copies of some subgraph S that can be labeled by a single label. We focus on minimizing the index of S - an inverse of its density rounded up. We establish lower bounds and prove that our constructions are optimal or almost optimal, both for the index of S and for the interleaving degree. We identify related combinatorial questions and advance conjectures.", "date": "2002-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2002.ETR046", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2002.ETR046", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr_046.ps", "url": "https://authors.library.caltech.edu/records/bak03-gez83/files/etr_046.ps" }, "related_objects": [ { "basename": "etr046.pdf", "url": "https://authors.library.caltech.edu/records/bak03-gez83/files/etr046.pdf" } ], "pub_year": "2002", "author_list": "Slivkins, Aleksandrs and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/g4g98-68990", "eprint_id": 26078, "eprint_status": "archive", "datestamp": "2023-08-19 08:54:08", "lastmod": "2023-10-24 16:13:14", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Memory Allocation in Information Storage Networks", "ispublished": "unpub", "full_text_status": "public", "abstract": "We propose a file storage scheme which bounds the file-retrieving delays in a hetrerogeneous information network, under both fault-free and faulty circumstances. The scheme combines coding with storage for better performance. We study the memory allocation problem for the scheme, which is to decide how much data to store on each node, with the objective of minimizing the total amount of data stored in the network. This problem is NP-hard for general networks. We present three polynomial-time algorithms which solve the memory allocation problem for tree networks. The first two algorithms are for tree networks with and without upper bounds on nodes' memory sizes respectively. The third algorithm finds, among all the optimal solutions for the tree network, the solution that minimizes the greatest memory size of single nodes. By combining these memory allocation algorithms with known data-interleaving techniques, a complete solution to realize the file storage scheme in tree networks is established.", "date": "2002-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2002.ETR048", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2002.ETR048", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "ETR048.ps", "url": "https://authors.library.caltech.edu/records/g4g98-68990/files/ETR048.ps" }, "related_objects": [ { "basename": "ETR048.pdf", "url": "https://authors.library.caltech.edu/records/g4g98-68990/files/ETR048.pdf" } ], "pub_year": "2002", "author_list": "Jiang, Anxiao (Andrew) and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/1ryzf-n1606", "eprint_id": 26031, "eprint_status": "archive", "datestamp": "2023-08-19 08:53:30", "lastmod": "2023-10-24 16:11:36", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Franceschetti-M", "name": { "family": "Franceschetti", "given": "Massimo" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" }, { "id": "Schulman-L-J", "name": { "family": "Schulman", "given": "Leonard J." }, "orcid": "0000-0001-9901-2797" } ] }, "title": "Microcellular Systems, Random Walks, and Wave Propagation", "ispublished": "unpub", "full_text_status": "public", "abstract": "As the number of users of wireless services increases, the concept of using smaller\ncell sizes becomes especially attractive because of its potential for capacity increase.\nCurrent technology allows to build base stations for small cells in a cost effective\nway, and telecommunication companies have started exploiting the new microcellular\nconcept in providing coverage to densely populated areas. Prediction of propagation\ncharacteristics in this new scenario is essential for accurate link budget calculations in\nnetwork planning.\nIn this paper a new, simple model of wave propagation for microcellular systems\nis applied to predict the path loss of a wireless channel. The model does not rely on\nthe classical theory of electromagnetic wave propagation, but it is entirely based on\nprobability theory. We consider the canonical scenario of a random environment of\npartially absorbing scatterers and model the trajectory of each photon in the system\nas a random walk. This model leads to a path loss formula that rather accurately (in comparison to other models and experimental data) describes the smooth transition\nof power attenuation from an inverse square law with the distance to the transmitter\nto an exponential attenuation as this distance is increased. This result can justify\nempirical formulas that are often used for path loss prediction, characterized by a\nbreakpoint distance at which the exponent of a power law is increased from a value of\napproximately 2 to a value in the range of 4 to 10.\nTheoretical predictions of the model are validated by showing agreement with experimental data collected in the city of Rome, Italy.", "date": "2002-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2002.ETR045", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2002.ETR045", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr045.pdf", "url": "https://authors.library.caltech.edu/records/1ryzf-n1606/files/etr045.pdf" }, "related_objects": [ { "basename": "etr045.ps", "url": "https://authors.library.caltech.edu/records/1ryzf-n1606/files/etr045.ps" } ], "pub_year": "2002", "author_list": "Franceschetti, Massimo; Bruck, Jehoshua; et el." }, { "id": "https://authors.library.caltech.edu/records/s09d6-97m41", "eprint_id": 26034, "eprint_status": "archive", "datestamp": "2023-08-19 08:53:48", "lastmod": "2023-10-24 16:11:43", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Foltz-K", "name": { "family": "Foltz", "given": "Kevin" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Time-Division is Better Than Frequency-Division for Periodic Internet Broadcasting", "ispublished": "unpub", "full_text_status": "public", "abstract": "The broadcast disk provides an effective way to transmit information from a server to many\nclients. Information is broadcast cyclically and clients pick the information they need out of the\nbroadcast. An example of such a system is a wireless web service where web servers broadcast\nto browsing clients. We consider two ways to send items over a broadcast channel and compare\nthem using the metric of expected waiting time. The first is frequency-division, where each\nitem is broadcast on its own subchannel of lower bandwidth. We find the optimal allocation of\nbandwidth to the subchannels using this method. Then we look at time-division, where items\nare sent sequentially on a single full-bandwidth channel. For items of equal length, we show\nthat for any frequency-division broadcast schedule, we can find a better time-division schedule.\nThus time-division is better than frequency-division.", "date": "2002-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2002.ETR042", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2002.ETR042", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr042.pdf", "url": "https://authors.library.caltech.edu/records/s09d6-97m41/files/etr042.pdf" }, "related_objects": [ { "basename": "etr042.ps", "url": "https://authors.library.caltech.edu/records/s09d6-97m41/files/etr042.ps" } ], "pub_year": "2002", "author_list": "Foltz, Kevin and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/j0t0g-0px95", "eprint_id": 26039, "eprint_status": "archive", "datestamp": "2023-08-19 07:10:41", "lastmod": "2023-10-24 16:11:54", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Franceschetti-M", "name": { "family": "Franceschetti", "given": "Massimo" } }, { "id": "Cook-M", "name": { "family": "Cook", "given": "Matthew" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "A Geometric Theorem for Approximate Disk Covering Algorithms", "ispublished": "unpub", "full_text_status": "public", "abstract": "We present a basic theorem in combinatorial geometry that leads to a family of approximation algorithms for the the geometric disk covering problem. These algorithms exhibit constant approximation factors, with a wide range of their choices. This flexibility allows to achieve a running time that compares favourably with those of existing procedures..", "date": "2001-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2001.ETR035", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2001.ETR035", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr035.pdf", "url": "https://authors.library.caltech.edu/records/j0t0g-0px95/files/etr035.pdf" }, "related_objects": [ { "basename": "etr035.ps", "url": "https://authors.library.caltech.edu/records/j0t0g-0px95/files/etr035.ps" } ], "pub_year": "2001", "author_list": "Franceschetti, Massimo; Cook, Matthew; et el." }, { "id": "https://authors.library.caltech.edu/records/2kpct-h9a29", "eprint_id": 26037, "eprint_status": "archive", "datestamp": "2023-08-19 07:10:28", "lastmod": "2023-10-24 16:11:49", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Booth-L", "name": { "family": "Booth", "given": "Lorna" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" }, { "id": "Franceschetti-M", "name": { "family": "Franceschetti", "given": "Massimo" } }, { "id": "Meester-R", "name": { "family": "Meester", "given": "Ronald" } } ] }, "title": "Covering Algorithms, Continuum Percolation, and the Geometry of Wireless Networks.", "ispublished": "unpub", "full_text_status": "public", "abstract": "Continuum percolation models where each point of a two-dimensional Poisson\npoint process is the center of a disc of given (or random) radius r, have been\nextensively studied. In this paper, we consider the generalization in which a\ndeterministic algorithm (given the points of the point process) places the discs\non the plane, in such a way that each disc covers at least one point of the point\nprocess and that each point is covered by at least one disc. This gives a model\nfor wireless communication networks, which was the original motivation to study\nthis class of problems.\nWe look at the percolation properties of this generalized model, showing the\nalmost sure non-existence of an unbounded connected component of discs for\nsmall values of the density lambda of the Poisson point process, for any covering\nalgorithm. In general, it turns out not to be true that unbounded connected\ncomponents arise when lambda is taken sufficiently high. However, we identify some\nlarge families of covering algorithms, for which such an unbounded component\ndoes arise for large values of lambda. \nWe show how a simple scaling operation can change the percolation properties\nof the model, leading to the almost sure existence of an unbounded connected\ncomponent for large values of lambda, for any covering algorithm.\nFinally, we show that a large class of covering algorithms, that arise in many\npractical applications, can get arbitrarily close to achieving a minimal density of\ncovering discs. We also show (constructively) the existence of algorithms that\nachieve this minimal density.", "date": "2001-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2001.ETR037", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2001.ETR037", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr037.pdf", "url": "https://authors.library.caltech.edu/records/2kpct-h9a29/files/etr037.pdf" }, "related_objects": [ { "basename": "etr037.ps", "url": "https://authors.library.caltech.edu/records/2kpct-h9a29/files/etr037.ps" } ], "pub_year": "2001", "author_list": "Booth, Lorna; Bruck, Jehoshua; et el." }, { "id": "https://authors.library.caltech.edu/records/c0g4e-34404", "eprint_id": 26036, "eprint_status": "archive", "datestamp": "2023-08-19 07:10:21", "lastmod": "2023-10-24 16:11:47", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Jiang-A-A", "name": { "family": "Jiang", "given": "Anxiao (Andrew)" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Diversity Coloring for Distributed Storage in Mobile Networks", "ispublished": "unpub", "full_text_status": "public", "abstract": "Storing multiple copies of files is crucial for ensuring quality of service for data storage in\nmobile networks. This paper proposes a new scheme, called the K-out-of-N file distribution scheme, for\nthe placement of files. In this scheme files are splitted, and Reed-Solomon codes or other maximum\ndistance seperable (MDS) codes are used to produce file segments containing parity information. Multiple\ncopies of the file segments are stored on gateways in the network in such a way that every gateway can\nretrieve enough file segments from itself and its neighbors within a certain amount of hops for\nreconstructing the orginal files. The goal is to minimize the maximum number of hops it takes for any\ngateway to get enough file segments for the file reconstruction.\nWe formulate the K-out-of-N file distribution scheme as a coloring problem we call diversity coloring.\nA diversity coloring is defined to be optimal if it uses the smallest number of colors. Upper and lower\nbounds on the performance of diversity coloring for general graphs are studied. Diversity coloring\nalgorithms for several special classes of graphs - trees, rings and tori - are presented, all of which \n\nhave linear time complexity. Both the algorithm for trees and the algorithm for rings output optimal \n\ndiversity colorings. The algorithm for tori guarantees to output optimal diversity coloring when the \n\nsizes of tori are sufficiently large.", "date": "2001-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2001.ETR038", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2001.ETR038", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr038.pdf", "url": "https://authors.library.caltech.edu/records/c0g4e-34404/files/etr038.pdf" }, "related_objects": [ { "basename": "etr038.ps", "url": "https://authors.library.caltech.edu/records/c0g4e-34404/files/etr038.ps" } ], "pub_year": "2001", "author_list": "Jiang, Anxiao (Andrew) and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/e7s3t-e9466", "eprint_id": 26038, "eprint_status": "archive", "datestamp": "2023-08-19 07:10:35", "lastmod": "2023-10-24 16:11:52", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Mukhtar-S", "name": { "family": "Mukhtar", "given": "Saleem" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Frequency Modulation for Asynchronous Data Transfer", "ispublished": "unpub", "full_text_status": "public", "abstract": "Consider a communication channel that consists of several subchannels transmitting simultaneously and\nasynchronously. As an example of this scheme, consider a board with two chips (transmitter and receiver). The subchannels represent wires connecting between the chips where differences in the lengths of the wires might result in asynchronous reception. The contribution of this paper is a scheme which allows pipelined asynchronous communication at very high rates even when the amount of skew is arbitrarily large and unknown apriori. Insensitivity to delay is accomplished by encoding data in the frequency of the signal, as opposed to amplitude. The theoretical questions that are answered are what rates can be accomplished. In doing so we have extended the work of Capocelli and Spickerman on generalized Fibonacci numbers. The second question that we answer is\nhow to encode data efficiently in the frequency of the signal. For the purposes of encoding and decoding \nwe use variable length to variable length prefix-free codes. We have provided an algorithm based on \ninteger linear programming for constructing such codes. In essence, we have formulated a scheme which is easy to implement and allows for asynchronous data transfer at very high rates. Potential applications are in on-chip, on-board and board to board communication, enabling much higher bandwidths.", "date": "2001-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2001.ETR036", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2001.ETR036", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr036.pdf", "url": "https://authors.library.caltech.edu/records/e7s3t-e9466/files/etr036.pdf" }, "related_objects": [ { "basename": "etr036.ps", "url": "https://authors.library.caltech.edu/records/e7s3t-e9466/files/etr036.ps" } ], "pub_year": "2001", "author_list": "Mukhtar, Saleem and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/6yhbd-vjn12", "eprint_id": 26035, "eprint_status": "archive", "datestamp": "2023-08-19 07:10:13", "lastmod": "2023-10-24 16:11:45", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Mukhtar-S", "name": { "family": "Mukhtar", "given": "Saleem" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Interval Modulation Coding", "ispublished": "unpub", "full_text_status": "public", "abstract": "In this paper we introduce a new paradigm for\nstorage and communication. We call this paradigm Interval\nModulation Coding. Both in the context of \ncommunication and storage, one needs to measure the elapsed time\nbetween voltage transitions or voltage pulses. \nConventionally, this measurement is made by a clock, by counting clock\npulses. Analog circuits (or clocks of higher frequency) can\nalso be used to measure elapsed time. And in this case the\nset of permissible time intervals no longer has to consist of\nconsecutive integer multiples of the clock period but can be\nchosen in accordance with a probabilistic model of \nmeasurement error. We will show that this can potentially provide\nsubstantial improvements in terms of bandwitdth and \nstorage density over coding techniques deployed in real storage\nand communication systems. We provide a mechanism for\nencoding and decoding data based on variable length to \nvariable length prefix free codes. We show that such codes can\nbe constructed using integer linear programming. From a\ntheoretical standpoint, we study the linear programming \nrelaxation of the integer linear program associated with code\nconstruction. We provide an efficient algorithm for \ndetermining if the linear programming relaxation is feasible and\nan efficient algorithm for solving the linear programming\nrelaxation, assuming it is feasible.", "date": "2001-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2001.ETR040", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2001.ETR040", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr040.pdf", "url": "https://authors.library.caltech.edu/records/6yhbd-vjn12/files/etr040.pdf" }, "related_objects": [ { "basename": "etr040.ps", "url": "https://authors.library.caltech.edu/records/6yhbd-vjn12/files/etr040.ps" } ], "pub_year": "2001", "author_list": "Mukhtar, Saleem and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/5bnpk-3aj79", "eprint_id": 26041, "eprint_status": "archive", "datestamp": "2023-08-19 05:14:15", "lastmod": "2023-10-24 16:11:58", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Blaum-M", "name": { "family": "Blaum", "given": "Mario" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Coding for Tolerance and Detection of Skew in Parallel Asynchronous Communications", "ispublished": "unpub", "full_text_status": "public", "abstract": "Abstract to be added.", "date": "2000-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2000.ETR033", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2000.ETR033", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr033.ps", "url": "https://authors.library.caltech.edu/records/5bnpk-3aj79/files/etr033.ps" }, "related_objects": [ { "basename": "etr033.pdf", "url": "https://authors.library.caltech.edu/records/5bnpk-3aj79/files/etr033.pdf" } ], "pub_year": "2000", "author_list": "Blaum, Mario and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/03dfq-5x652", "eprint_id": 26040, "eprint_status": "archive", "datestamp": "2023-08-19 05:14:08", "lastmod": "2023-10-24 16:11:56", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Foltz-K", "name": { "family": "Foltz", "given": "Kevin" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Splitting Schedules for Internet Broadcast Communication", "ispublished": "unpub", "full_text_status": "public", "abstract": "The broadcast disk provides an effective way to transmit information from a server to many\nclients. Information is broadcast cyclically and clients pick the information they need out of the\nbroadcast. An example of such a system is a wireless web service where web servers broadcast\nto browsing clients. Work has been done to schedule the broadcast of information in a way\nthat minimizes the expected waiting time of the clients. This work has treated the information\nas indivisible blocks. We propose a new way to schedule the broadcast of information, which\ninvolves splitting items into smaller pieces that need not be broadcast consecutively. This relaxes\nthe previous restrictions, and allows us to have better schedules with lower expected waiting\ntimes. We look at the case of two items of the same length, each split into two halves, and show\nthat we can achieve optimal performance by choosing the appropriate schedule from a small set\nof schedules. We derive a set of optimal schedules and show which one to use, as a function of\nthe demand probabilities. In fact we prove the surprising result that there are only two possible\ntypes of optimal cyclic schedules for items 1 and 2. These start with 1122 and 122122. For\nexample, with demand probabilities p subscript1 = .08 and p subscript2 = .92, the best order to use in broadcasting\nthe halves of items 1 and 2 is a cyclic schedule with cycle 122122222. We also show that much\nof the analysis remains the same if we consider items of different lengths. We present numerical\ndata that suggests that the set of optimal schedules for different length items also consists of\ntwo types, starting with 1122 and 122122. For example, with demand probabilities p subscriptl = .08 and\np subscript2 = .92 as above but lsubscript2 = 2lsubscript1, the best schedule is 11222222.", "date": "2000-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:2000.ETR034", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:2000.ETR034", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr034.pdf", "url": "https://authors.library.caltech.edu/records/03dfq-5x652/files/etr034.pdf" }, "related_objects": [ { "basename": "etr034.ps", "url": "https://authors.library.caltech.edu/records/03dfq-5x652/files/etr034.ps" } ], "pub_year": "2000", "author_list": "Foltz, Kevin and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/mys1x-vty92", "eprint_id": 26042, "eprint_status": "archive", "datestamp": "2023-08-19 03:53:04", "lastmod": "2023-10-24 16:12:00", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Franceschetti-M", "name": { "family": "Franceschetti", "given": "Massimo" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "A Possible Solution to the Impossible Membership Problem", "ispublished": "unpub", "full_text_status": "public", "abstract": "This paper presents a solvable specification and gives an algorithm for the Group\nMembership Problem in asynchronous systems with crash failures. Our specification\nrequires processes to maintain a consistent history in their sequence of views. This\nallows processes to order failures and recoveries in time and simplifies the programming\nof high level applications. Previous work proved that the Group Membership Problem\ncannot be solved in asynchronous systems with crash failures. We circumvent this\nimpossibility result building a weaker, yet non-trivial specification. We show that our\nsolution is an improvement upon previous attempts to solve this problem using a weaker\nspecification. We also relate our solution to other methods, and give a classification of\nprogress properties that can be achieved under different models.", "date": "1999-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1999.ETR032", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1999.ETR032", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr032.ps", "url": "https://authors.library.caltech.edu/records/mys1x-vty92/files/etr032.ps" }, "related_objects": [ { "basename": "etr032.pdf", "url": "https://authors.library.caltech.edu/records/mys1x-vty92/files/etr032.pdf" } ], "pub_year": "1999", "author_list": "Franceschetti, Massimo and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/sykbz-p5r83", "eprint_id": 26045, "eprint_status": "archive", "datestamp": "2023-08-19 03:53:23", "lastmod": "2023-10-24 16:12:07", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Bohossian-V", "name": { "family": "Bohossian", "given": "Vasken" } }, { "id": "Fan-C-C", "name": { "family": "Fan", "given": "Charles C." } }, { "id": "LeMahieu-P-S", "name": { "family": "LeMahieu", "given": "Paul S." } }, { "id": "Riedel-M-D", "name": { "family": "Riedel", "given": "Marc D." }, "orcid": "0000-0002-3318-346X" }, { "id": "Xu-L", "name": { "family": "Xu", "given": "Lihao" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Computing in the RAIN: A Reliable Array of Independent Nodes", "ispublished": "unpub", "full_text_status": "public", "abstract": "The RAIN project is a research collaboration between Caltech and NASA-JPL on \ndistributed computing and data storage systems for future spaceborne missions. The goal of the\nproject is to identify and develop key building blocks for reliable distributed systems built with\ninexpensive off-the-shelf components. The RAIN platform consists of a heterogeneous cluster\nof computing and/or storage nodes connected via multiple interfaces to networks configured\nin fault-tolerant topologies. The RAIN software components run in conjunction with \noperating system services and standard network protocols. Through software-implemented fault\ntolerance, the system tolerates multiple node, link, and switch failures, with no single point of\nfailure. The RAIN technology has been transfered to RAINfinity, a start-up company focusing\non creating clustered solutions for improving the performance and availability of Internet data\ncenters.\nIn this paper we describe the following contributions: 1) fault-tolerant interconnect topologies and communication protocols providing consistent error reporting of link failures; 2) fault\nmanagement techniques based on group membership; and 3) data storage schemes based on\ncomputationally efficient error-control codes. We present several proof-of-concept applications:\nhighly available video and web servers, and a distributed checkpointing system.", "date": "1999-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1999.ETR029", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1999.ETR029", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr029.pdf", "url": "https://authors.library.caltech.edu/records/sykbz-p5r83/files/etr029.pdf" }, "related_objects": [ { "basename": "etr029.ps", "url": "https://authors.library.caltech.edu/records/sykbz-p5r83/files/etr029.ps" } ], "pub_year": "1999", "author_list": "Bohossian, Vasken; Fan, Charles C.; et el." }, { "id": "https://authors.library.caltech.edu/records/68ta2-vg371", "eprint_id": 26043, "eprint_status": "archive", "datestamp": "2023-08-19 03:53:10", "lastmod": "2023-10-24 16:12:02", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Gibson-M-A", "name": { "family": "Gibson", "given": "Michael A." } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Efficient Exact Stochastic Simulation of Chemical Systems with Many Species and Many Channels", "ispublished": "unpub", "full_text_status": "public", "abstract": "There are two fundamental ways to view coupled systems of chemical equations: as continuous, represented\nby differential equations whose variables are concentrations, or as discrete, represented by stochastic \n\nprocesses whose variables are numbers of molecules. Although the former is by far more common, systems \n\nwith very small numbers of molecules are important in some applications, e.g., in small biological cells \n\nor in surface processes. In both views, most complicated systems with multiple reaction channels and \n\nmultiple chemical species cannot be solved analytically. There are exact numerical simulation methods to \n\nsimulate trajectories of discrete, stochastic systems, methods that are rigorously equivalent to the \n\nMaster Equation approach, but they do not scale well to systems with many reaction pathways.\n\nThis paper presents the Next Reaction Method, an exact algorithm to simulate coupled chemical reactions \n\nthat is also efficient: it (a) uses only a single random number per simulation event, and (b) takes time \n\nproportional to the logarithm of the number of reactions, not to the number of reactions itself. The \n\nNext Reaction Method is extended to include time-dependent rate constants and non-Markov processes and \n\nit is applied to a sample application in biology: the lysis/lysogeny decision circuit of lambda phage. \n\nWhen run on lambda the Next Reaction Method requires approximately 1/15th as many operations as a \n\nstandard implementation of the existing methods.", "date": "1999-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1999.ETR031", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1999.ETR031", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr031.pdf", "url": "https://authors.library.caltech.edu/records/68ta2-vg371/files/etr031.pdf" }, "related_objects": [ { "basename": "etr031.ps", "url": "https://authors.library.caltech.edu/records/68ta2-vg371/files/etr031.ps" } ], "pub_year": "1999", "author_list": "Gibson, Michael A. and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/1nev3-5px41", "eprint_id": 26044, "eprint_status": "archive", "datestamp": "2023-08-19 03:53:16", "lastmod": "2023-10-24 16:12:04", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Foltz-K", "name": { "family": "Foltz", "given": "Kevin" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Splitting the Scheduling Headache", "ispublished": "unpub", "full_text_status": "public", "abstract": "The broadcast disk provides an effective way to transmit information from a server to many\nclients. Information is broadcast cyclically and clients pick the information they need out of the\nbroadcast. An example of such a system is a wireless web service where web servers broadcast to\nbrowsing clients. Work has been done to schedule the information broadcast so as to minimize\nthe expected waiting time of the clients. This work has treated the information as indivisible\nblocks that are transmitted in their entirety. We propose a new way to schedule the broadcast of\ninformation, which involves splitting items into smaller sub-items, which need not be broadcast\nimmediately after each other. This relaxes the previous restrictions, and hence allows us to\nhave better schedules with lower expected waiting times. We look at the case of two items of\nthe same length, each split into two halves, and show that we can achieve optimal performance\nby choosing the appropriate schedule from a small set of schedules. We derive a set of optimal\nschedules and show which one to use, as a function of the demand probabilities. In fact we prove\nthe surprising result that there are only two possible types of optimal cyclic schedules for items\n1 and 2. The first starts with 1122 and the second with 122122. For example, with demand\nprobabilities p1 = .19 and p2 = 31, the best order to use in broadcasting the halves of items 1\nand 2 is a cyclic schedule with cycle 122122.", "date": "1999-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1999.ETR030", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1999.ETR030", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr030.pdf", "url": "https://authors.library.caltech.edu/records/1nev3-5px41/files/etr030.pdf" }, "related_objects": [ { "basename": "etr030.ps", "url": "https://authors.library.caltech.edu/records/1nev3-5px41/files/etr030.ps" } ], "pub_year": "1999", "author_list": "Foltz, Kevin and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/gvtmd-4r446", "eprint_id": 26051, "eprint_status": "archive", "datestamp": "2023-08-19 02:22:39", "lastmod": "2023-10-24 16:12:19", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "LeMahieu-P-S", "name": { "family": "LeMahieu", "given": "Paul S." } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "A Consistent History Link Connectivity Protocol", "ispublished": "unpub", "full_text_status": "public", "abstract": "The RAIN (Reliable Array of Independent Nodes) project at Caltech is focusing on creating\nhighly reliable distributed systems by leveraging commercially available personal computers.\nworkstations and interconnect technologies. In particular, the issue of reliable communication\nis addressed by introducing redundancy in the form of multiple network interfaces per compute\nnode.\nWhen using compute nodes with multiple network connections the question of how to \ndetermine connectivity between nodes arises. We examine a connectivity protocol that guarantees\nthat each side of a point-to-point connection sees the same history of activity over the commu-\nnication channel. In other words, we maintain a consistent history of the state of the \ncommunication channel. At any give moment in time the histories as seen by each side are guaranteed\nto be identical to within some number of transitions. This bound on how much one side may\nlead or lag the other is the slack.\nOur main contributions are: (i) a simple, stable protocol for monitoring connectivity that\nmaintains a consistent history with bounded slack. and (ii) proofs that this protocol exhibits\ncorrectness, bounded slack, and stability.", "date": "1998-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1998.ETR023", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1998.ETR023", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "collection": "CaltechAUTHORS", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group", "value": "Parallel and Distributed Systems Group" } ] }, "primary_object": { "basename": "etr023.ps", "url": "https://authors.library.caltech.edu/records/gvtmd-4r446/files/etr023.ps" }, "related_objects": [ { "basename": "etr023.pdf", "url": "https://authors.library.caltech.edu/records/gvtmd-4r446/files/etr023.pdf" } ], "pub_year": "1998", "author_list": "LeMahieu, Paul S. and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/6z835-5g480", "eprint_id": 26050, "eprint_status": "archive", "datestamp": "2023-08-19 02:22:33", "lastmod": "2023-10-24 16:12:17", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Franceschetti-M", "name": { "family": "Franceschetti", "given": "Massimo" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "A Leader Election Protocol for Fault Recovery in Asynchronous Fully-Connected Networks", "ispublished": "unpub", "full_text_status": "public", "abstract": "We introduce a new algorithm for consistent failure detection in asynchronous\nsystems. Informally, consistent failure detection requires processes in a distributed system to distinguish between two different populations: a fault free\npopulation and a faulty one.\nThe major contribution of this paper is in combining ideas from group \nmembership and leader election, in order to have an election protocol for a \nfault manager whose convergence is delayed until a new consistent view of the connectivity\nof the network is established by all processes. In our algorithm a group of \nprocesses agrees upon the failed population of the system, and then gives to a unique\nleader, called the fault manager, the possibility of executing distributed tasks in\na centralized way.\nThis research and the new perspective that we propose are driven by the\nstudy of an actual system, the Caltech RAIN (Reliable Array of Independent\nNodes), on which our protocol has been implemented in order to perform fault\nrecovery in distributed checkpointing. Other potential applications include fault\ntolerant distributed database services and fault tolerant distributed web servers.", "date": "1998-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1998.ETR024", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1998.ETR024", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr024.pdf", "url": "https://authors.library.caltech.edu/records/6z835-5g480/files/etr024.pdf" }, "related_objects": [ { "basename": "etr024.ps", "url": "https://authors.library.caltech.edu/records/6z835-5g480/files/etr024.ps" } ], "pub_year": "1998", "author_list": "Franceschetti, Massimo and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/39v3v-60q25", "eprint_id": 26047, "eprint_status": "archive", "datestamp": "2023-08-19 02:22:16", "lastmod": "2023-10-24 16:12:11", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Gibson-M-A", "name": { "family": "Gibson", "given": "Michael A." } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "An Efficient Algorithm for Generating Trajectories of Stochastic Gene Regulation Reactions", "ispublished": "unpub", "full_text_status": "public", "abstract": "Systems of weakly coupled chemical equations occur in gene regulation and other biological\nsystems. For small numbers of molecules (as in a small cell), the usual differential equations\napproach to chemical kinetics must be replaced with a stochastic approach. To deal with this\nkind of system, one generates trajectories through stochastic phase space. By generating a large\nenough number of trajectories, one can understand the statistics of the behavior of the complex,\nnon-linear system.\nThe algorithms for dealing with sparsely connected stochastic processes are not as advanced\nas those for sparse deterministic processes. In particular. the existing algorithm of choice for\ngenerating trajectories, which is not optimized in any way for sparseness, is O(rE), where r is\nthe number of reactions and E is the number of reaction events in the trajectory. \\Ye present\ntwo algorithms of O(r + Elogr), one of which is a simple extension of the existing algorithm,\nand the other of which is more subtle. The latter is more easily extended to include stochastic\nprocesses of different types.\nWe apply our faster algorithm to a model of bacteriophage lambda and are able to run the\nsame calculations on a cluster of desktop workstations that previously required a supercomputer.\nThis allows us to run more complicated calculations than could be done previously. As an\nexample of this, we analyse the sensitivity of the lambda model to the values of several of\nits parameters. We find that the model is relatively insensitive to changes in the translation\nrate, protein dimerization rates and protein degradation rates; is somewhat sensitive to the\ntranscription rate. and is extremely sensitive to the average number of proteins per mRNA\ntranscript.", "date": "1998-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1998.ETR026", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1998.ETR026", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr026.ps", "url": "https://authors.library.caltech.edu/records/39v3v-60q25/files/etr026.ps" }, "related_objects": [ { "basename": "etr026.pdf", "url": "https://authors.library.caltech.edu/records/39v3v-60q25/files/etr026.pdf" } ], "pub_year": "1998", "author_list": "Gibson, Michael A. and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/re8wp-xm408", "eprint_id": 26053, "eprint_status": "archive", "datestamp": "2023-08-19 02:22:52", "lastmod": "2023-10-24 16:12:24", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "LeMahieu-P-S", "name": { "family": "LeMahieu", "given": "Paul S." } }, { "id": "Bohossian-V", "name": { "family": "Bohossian", "given": "Vasken" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Fault-Tolerant Switched Local Area Networks", "ispublished": "unpub", "full_text_status": "public", "abstract": "The RAIN (Reliable Array of Independent Nodes) project at Caltech is focusing on creating highly \n\nreliable distributed systems by leveraging commercially available personal computers, workstations and \n\ninterconnect technologies. In particular; the issue of reliable communication is addressed by \n\nintroducing redundancy in the form of multiple network interfaces per computer node. When using compute \n\nnodes with multiple network connections\nthe question of how to best connect these nodes to a given network of switches arises. We examine \n\nnetworks of\nswitches (e.g. based on Myrinet technology) and focus on degree two compute nodes (two network adaptor \n\ncards\nper node). Our primary goal is to create networks that are as resistant as possible to partitioning.\nOur main contributions are: (i) a construction for degree-2 compute nodes connected by a ring network of\nswitches of degree 4 that can tolerate any 3 switch failures without partitioning the nodes into \n\ndisjoint sets, (ii)\na proof that this construction is optimal in the sense that no construction can tolerate more switch \n\nfailures while\navoiding partitioning and (iii) generalizations of this construction to arbitrary switch and node \n\ndegrees and to\nother switch networks, in particular; to a fully-connected network of switches.", "date": "1998-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1998.ETR021", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1998.ETR021", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr021.pdf", "url": "https://authors.library.caltech.edu/records/re8wp-xm408/files/etr021.pdf" }, "related_objects": [ { "basename": "etr021.ps", "url": "https://authors.library.caltech.edu/records/re8wp-xm408/files/etr021.ps" } ], "pub_year": "1998", "author_list": "LeMahieu, Paul S.; Bohossian, Vasken; et el." }, { "id": "https://authors.library.caltech.edu/records/syxb8-kqh08", "eprint_id": 26046, "eprint_status": "archive", "datestamp": "2023-08-19 02:22:09", "lastmod": "2023-10-24 16:12:08", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Xu-L", "name": { "family": "Xu", "given": "Lihao" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Improving the Performance of Data Servers Using Array Codes", "ispublished": "unpub", "full_text_status": "public", "abstract": "This paper discusses improving performance (throughput) of data server systems by\nintroducing proper data redundancy into the system. General performance properties of a\nserver system with redundant data are described. We show that proper data redundancy\nin a server system can significantly improve the performance, in addition to the reliability\nof the system. Two problems related to the performance together with their solutions\nare proposed, namely, the problems of efficient data distribution scheme for the severs\nand data acquisition scheme for the client. Both schemes utilize array codes, a class of\nerror-correcting codes whose encoding and decoding procedures only use simple binary\nexclusive-OR operations, which can be implemented efficiently in software and/or hardware.\nConstruction of general MDS array codes suitable for the both schemes is discussed. A new\nproperty of MDS array codes, called the strong MDS property, is also defined to improve\nthe data acquisition performance. A method for modeling data server performance and the\nrelated experimental results are presented as well.", "date": "1998-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1998.ETR027", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1998.ETR027", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "collection": "CaltechAUTHORS", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group", "value": "Parallel and Distributed Systems Group" } ] }, "primary_object": { "basename": "etr027.ps", "url": "https://authors.library.caltech.edu/records/syxb8-kqh08/files/etr027.ps" }, "related_objects": [ { "basename": "etr027.pdf", "url": "https://authors.library.caltech.edu/records/syxb8-kqh08/files/etr027.pdf" } ], "pub_year": "1998", "author_list": "Xu, Lihao and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/jcwj7-97e76", "eprint_id": 26048, "eprint_status": "archive", "datestamp": "2023-08-19 02:22:21", "lastmod": "2023-10-24 16:12:12", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Xu-L", "name": { "family": "Xu", "given": "Lihao" } }, { "id": "Bohossian-V", "name": { "family": "Bohossian", "given": "Vasken" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" }, { "id": "Wagner-D-G", "name": { "family": "Wagner", "given": "David G." } } ] }, "title": "Low Density MDS Codes and Factors of Complete Graphs", "ispublished": "unpub", "full_text_status": "public", "abstract": "We reveal an equivalence relation between the construction of a new class of low density\nMDS array codes, that we call B-Code, and a combinatorial problem known as perfect one-\nfactorization of complete graphs. We use known perfect one-factors of complete graphs to\ncreate constructions and decoding algorithms for both B-Code and its dual code. B-Code and\nits dual are optimal in the sense that (i) they are MDS, (ii) they have an optimal encoding\nproperty, i.e., the number of the parity bits that are affected by change of a single information\nbit is minimal and (iii) they have optimal length. The existence of perfect one-factorizations\nfor every complete graph with an even number of nodes is a 35 years long conjecture in graph\ntheory. The construction of B-codes of arbitrary odd length will provide an affirmative answer\nto the conjecture.", "date": "1998-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1998.ETR025", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1998.ETR025", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "collection": "CaltechAUTHORS", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group", "value": "Parallel and Distributed Systems Group" } ] }, "primary_object": { "basename": "etr025.ps", "url": "https://authors.library.caltech.edu/records/jcwj7-97e76/files/etr025.ps" }, "related_objects": [ { "basename": "etr025.pdf", "url": "https://authors.library.caltech.edu/records/jcwj7-97e76/files/etr025.pdf" } ], "pub_year": "1998", "author_list": "Xu, Lihao; Bohossian, Vasken; et el." }, { "id": "https://authors.library.caltech.edu/records/47r2m-0k938", "eprint_id": 26052, "eprint_status": "archive", "datestamp": "2023-08-19 02:22:46", "lastmod": "2023-10-24 16:12:22", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Riedel-M-D", "name": { "family": "Riedel", "given": "Marc D." }, "orcid": "0000-0002-3318-346X" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Tolerating Faults in Counting Networks", "ispublished": "unpub", "full_text_status": "public", "abstract": "Counting networks were proposed by Aspnes, Herlihy and Shavit [4] as a technique\nfor solving multiprocessor coordination problems. We describe a method for tolerating an \narbitrary number of faults in counting networks. In our fault model, the following errors can occur\ndynamically in the counting network data structure: 1) a balancer's state is spuriously altered, 2)\na balancer's state can no longer be accessed.\nWe propose two approaches for tolerating faults. The first is based on a construction for a\nfault-tolerant balancer. We substitute a fault-tolerant balancer for every balancer in a counting\nnetwork. Thus, we transform a counting network with depth O(log to the power of 2 n); where n is the \n\nwidth, into a k-fault-tolerant counting network with depth O(k log to the power of 2 n).\n\nThe second approach is to append a correction network, built with fault-tolerant balancers, to a\ncounting network that may experience faults. We present a bound on the error in the output token\ndistribution of counting networks with faulty balancers (a generalization of the error bound for\nsorting networks with faulty comparators presented by Yao & Yao [21]. Given a token distribution\nwith a bounded error, the correction network produces a token distribution that is smooth, i.e.,\nthe number of tokens on each output wire differs by at most one (a weaker condition than the\nstep property). In order to tolerate k faults, the correction network has depth O (k to the power of 2 \n\nlog n) for a network of width n.", "date": "1998-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1998.ETR022", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1998.ETR022", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr022.ps", "url": "https://authors.library.caltech.edu/records/47r2m-0k938/files/etr022.ps" }, "related_objects": [ { "basename": "etr022.pdf", "url": "https://authors.library.caltech.edu/records/47r2m-0k938/files/etr022.pdf" } ], "pub_year": "1998", "author_list": "Riedel, Marc D. and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/c72rs-18e50", "eprint_id": 26049, "eprint_status": "archive", "datestamp": "2023-08-19 02:22:27", "lastmod": "2023-10-24 16:12:15", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Bohossian-V", "name": { "family": "Bohossian", "given": "Vasken" } }, { "id": "Riedel-M-D", "name": { "family": "Riedel", "given": "Marc D." }, "orcid": "0000-0002-3318-346X" }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Trading Weight Size for Circuit Depth: A Circuit for Comparison", "ispublished": "unpub", "full_text_status": "public", "abstract": "NOTE: Text or symbols not renderable in plain ASCII are indicated by [...]. Abstract included in .pdf \n\ndocument.\n\n\nWe present an explicit construction of a circuit for the COMPARISON function in [...],\nthe class of polynomial-size linear threshold circuits of depth two with polynomially growing\nweights. Goldmann and Karpinski proved that [...] in [4]. Hofmeister presented a\nsimplified version of the same result in [6]. We have further simplified the results of these two\npapers by limiting ourselves to the simulation of COMPARISON. Our construction has size\n[...], a significant improvement on the general bound of [...] in [6].", "date": "1998-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1998.ETR028", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1998.ETR028", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr028.pdf", "url": "https://authors.library.caltech.edu/records/c72rs-18e50/files/etr028.pdf" }, "related_objects": [ { "basename": "etr028.ps", "url": "https://authors.library.caltech.edu/records/c72rs-18e50/files/etr028.ps" } ], "pub_year": "1998", "author_list": "Bohossian, Vasken; Riedel, Marc D.; et el." }, { "id": "https://authors.library.caltech.edu/records/wa4cr-bce03", "eprint_id": 26055, "eprint_status": "archive", "datestamp": "2023-08-19 00:54:28", "lastmod": "2023-10-24 16:12:28", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Blaum-M", "name": { "family": "Blaum", "given": "Mario" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "MDS Array Codes for Correcting Criss-Cross Errors", "ispublished": "unpub", "full_text_status": "public", "abstract": "We present a family of MDS array codes of size (p - 1) x ( p - 1), p a prime number,\nand minimum criss-cross distance 3, i.e., the code is capable of correcting any row\nor column in error, without apriori knowledge of what type of error occurred. The\ncomplexity of the encoding and decoding algorithms is lower than that of known codes\nwith the same error-correcting power, since our algorithms are based on exclusive-\nOR operations over lines of different slopes. as opposed to algebraic operations over a\nfinite field. Tl'e also provide efficient encoding and decoding algorithms for errors and\nerasures.", "date": "1997-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1997.ETR019", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1997.ETR019", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "collection": "CaltechAUTHORS", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group", "value": "Parallel and Distributed Systems Group" } ] }, "primary_object": { "basename": "etr019.pdf", "url": "https://authors.library.caltech.edu/records/wa4cr-bce03/files/etr019.pdf" }, "related_objects": [ { "basename": "etr019.ps", "url": "https://authors.library.caltech.edu/records/wa4cr-bce03/files/etr019.ps" } ], "pub_year": "1997", "author_list": "Blaum, Mario and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/afjb1-vmg34", "eprint_id": 26056, "eprint_status": "archive", "datestamp": "2023-08-19 00:54:35", "lastmod": "2023-10-24 16:12:30", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Ho-C-T", "name": { "family": "Ho", "given": "Ching-Tien" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" }, { "id": "Agrawal-R", "name": { "family": "Agrawal", "given": "Rakesh" } } ] }, "title": "Partial-Sum Queries in OLAP Data Cubes Using Covering Codes", "ispublished": "unpub", "full_text_status": "public", "abstract": "A partial-sum query obtains the summation over a set of\nspecified cells of a data cube. We establish a connection \nbetween the covering problem in the theory of covering codes\nand the partial-sum problem and use this connection to \ndevise algorithms for the partial-sum problem with efficient\nspace-time trade-offs. For example, using our algorithms,\nwith 44% additional storage, the query response time can\nbe improved by about 12%; by roughly doubling the storage\nrequirement, the query response time can be improved by\nabout 34%.", "date": "1997-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1997.ETR018", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1997.ETR018", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr018.pdf", "url": "https://authors.library.caltech.edu/records/afjb1-vmg34/files/etr018.pdf" }, "related_objects": [ { "basename": "etr018.ps", "url": "https://authors.library.caltech.edu/records/afjb1-vmg34/files/etr018.ps" } ], "pub_year": "1997", "author_list": "Ho, Ching-Tien; Bruck, Jehoshua; et el." }, { "id": "https://authors.library.caltech.edu/records/w3av0-39113", "eprint_id": 26057, "eprint_status": "archive", "datestamp": "2023-08-19 00:54:42", "lastmod": "2023-10-24 16:12:32", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Bohossian-V", "name": { "family": "Bohossian", "given": "Vasken" } }, { "id": "Hasler-P", "name": { "family": "Hasler", "given": "Paul" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Programmable Neural Logic", "ispublished": "unpub", "full_text_status": "public", "abstract": "NOTE: Text or symbols not renderable in plain ASCII are indicated by [...]. Abstract is included in .pdf document.\n\n\nCircuits of threshold elements (Boolean input, Boolean output neurons) have been\nshown to be surprisingly powerful. Useful functions such as XOR, ADD and MULTIPLY\ncan be implemented by such circuits more efficiently than by traditional AND/OR cir-\ncuits. In view of that, we have designed and built a programmable threshold element.\nThe weights are stored on polysilicon floating gates, providing long-term retention \nwithout refresh. The weight value is increased using tunneling and decreased via hot electron\ninjection. A weight is stored on a single transistor allowing the development of dense\narrays of threshold elements. A 16-input programmable neuron was fabricated in the\nstandard 2 [...] double-poly, analog process available from MOSIS. A long term goal\nof this research is to incorporate programmable threshold elements, as building blocks in\nField Programmable Gate Arrays.", "date": "1997-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1997.ETR017", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1997.ETR017", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr017.pdf", "url": "https://authors.library.caltech.edu/records/w3av0-39113/files/etr017.pdf" }, "related_objects": [ { "basename": "etr017.ps", "url": "https://authors.library.caltech.edu/records/w3av0-39113/files/etr017.ps" } ], "pub_year": "1997", "author_list": "Bohossian, Vasken; Hasler, Paul; et el." }, { "id": "https://authors.library.caltech.edu/records/cz8ad-gxp22", "eprint_id": 26058, "eprint_status": "archive", "datestamp": "2023-08-19 00:54:47", "lastmod": "2023-10-24 16:12:35", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Blaum-M", "name": { "family": "Blaum", "given": "Mario" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" }, { "id": "Farrell-P", "name": { "family": "Farrell", "given": "Paddy" } } ] }, "title": "Two-Dimensional Interleaving Schemes with Repetitions", "ispublished": "unpub", "full_text_status": "public", "abstract": "We present 2-dimensional interleaving schemes, with repetition, for correcting 2-\ndimensional bursts (or clusters) of errors, where a cluster of errors is characterized by\nits area. A recent application of correction of 2-dimensional clusters appeared in the\ncontext of holographic storage. Known interleaving schemes are based on arrays of\nintegers with the property that every connected component of area t consists of distinct\nintegers. Namely, they are based on the use of 1-error-correcting codes. We extend this\nconcept by allowing repetitions within the arrays, hence, providing a trade-off between\nthe error-correcting capability of the codes and the degree of the interleaving schemes.", "date": "1997-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1997.ETR016", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1997.ETR016", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr016.pdf", "url": "https://authors.library.caltech.edu/records/cz8ad-gxp22/files/etr016.pdf" }, "pub_year": "1997", "author_list": "Blaum, Mario; Bruck, Jehoshua; et el." }, { "id": "https://authors.library.caltech.edu/records/tq5cm-6qa49", "eprint_id": 26054, "eprint_status": "archive", "datestamp": "2023-08-19 00:54:22", "lastmod": "2023-10-24 16:12:26", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Xu-L", "name": { "family": "Xu", "given": "Lihao" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "X-Code: MDS Array Codes with Optimal Encoding", "ispublished": "unpub", "full_text_status": "public", "abstract": "We present a new class of MDS array codes of size n x n (n a prime number)\ncalled X-Code. The X-Codes are of minimum column distance 3, namely, they can\ncorrect either one column error or two column erasures. The key novelty in X-code is\nthat it has a simple geometrical construction which achieves encoding/update optimal\ncomplexity, namely, a change of any single information bit affects exactly two parity\nbits. The key idea in our constructions is that all parity symbols are placed in rows\nrather than columns.", "date": "1997-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1997.ETR020", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1997.ETR020", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr020.pdf", "url": "https://authors.library.caltech.edu/records/tq5cm-6qa49/files/etr020.pdf" }, "related_objects": [ { "basename": "etr020.ps", "url": "https://authors.library.caltech.edu/records/tq5cm-6qa49/files/etr020.ps" } ], "pub_year": "1997", "author_list": "Xu, Lihao and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/3xy7r-6pq82", "eprint_id": 26061, "eprint_status": "archive", "datestamp": "2023-08-20 07:05:25", "lastmod": "2023-10-24 16:12:41", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Blaum-M", "name": { "family": "Blaum", "given": "Mario" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" }, { "id": "Rubin-K", "name": { "family": "Rubin", "given": "Kurt" } }, { "id": "Lenth-W", "name": { "family": "Lenth", "given": "Wilfried" } } ] }, "title": "A Coding Approach for Detection of Tampering in Write-Once Optical Disks", "ispublished": "unpub", "full_text_status": "public", "abstract": "We present coding methods for protecting against tampering of write-once optical\ndisks which turns them into a secure digital medium for applications where critical\ninformation must be stored in a way that presents or allows detection of an attempt at\nfalsification. Our method involves adding a small amount of redundancy to a modulated\nsector of data. This extra redundancy is not used for normal operation, but can be\nused for determining, say as a testimony in court, that a disk has not been tampered\nwith.", "date": "1996-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1996.ETR013", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1996.ETR013", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr013.pdf", "url": "https://authors.library.caltech.edu/records/3xy7r-6pq82/files/etr013.pdf" }, "related_objects": [ { "basename": "etr013.ps", "url": "https://authors.library.caltech.edu/records/3xy7r-6pq82/files/etr013.ps" } ], "pub_year": "1996", "author_list": "Blaum, Mario; Bruck, Jehoshua; et el." }, { "id": "https://authors.library.caltech.edu/records/zwzxc-fts62", "eprint_id": 26059, "eprint_status": "archive", "datestamp": "2023-08-20 07:05:13", "lastmod": "2023-10-24 16:12:37", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Bohossian-V", "name": { "family": "Bohossian", "given": "Vasken" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Algebraic Techniques for Constructing Minimal Weight Threshold Functions", "ispublished": "unpub", "full_text_status": "public", "abstract": "A linear threshold element computes a function that is a sign of a weighted sum of the\ninput variables. The weights are arbitrary integers; actually, they can be very big integers-\nexponential in the number of the input variables. While in the present literature a distinction is\nmade between the two extreme cases of linear threshold functions with polynomial-size weights\nas opposed to those with exponential-size weights, the best known lower bounds on the size\nof threshold circuits are for depth-2 circuits with small weights. Our main contributions are\ndevising two distinct methods for constructing threshold functions with minimal weights and\nfilling up the gap between polynomial and exponential weight growth by further refining the\nseparation. Namely, we prove that the class of linear threshold functions with polynomial-size\nweights can be divided into subclasses according to the degree of the polynomial. In fact, we\nprove a more general result-that there exists a minimal weight linear threshold function for\nany arbitrary number of inputs and any weight size.", "date": "1996-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1996.ETR015", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1996.ETR015", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr015.pdf", "url": "https://authors.library.caltech.edu/records/zwzxc-fts62/files/etr015.pdf" }, "related_objects": [ { "basename": "etr015.ps", "url": "https://authors.library.caltech.edu/records/zwzxc-fts62/files/etr015.ps" } ], "pub_year": "1996", "author_list": "Bohossian, Vasken and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/34cns-m4519", "eprint_id": 26063, "eprint_status": "archive", "datestamp": "2023-08-20 07:05:37", "lastmod": "2023-10-24 16:12:46", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Xu-L", "name": { "family": "Xu", "given": "Lihao" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Deterministic Voting in Distributed Systems Using Error-Correcting Codes", "ispublished": "unpub", "full_text_status": "public", "abstract": "Distributed voting is an important problem in reliable computing. In an N \nModular Redundant (NMR) system, the N computational modules execute identical tasks\nand they need to periodically vote on their current states. In this paper, we propose a\ndeterministic majority voting algorithm for NMR systems. Our voting algorithm uses\nerror-correcting codes to drastically reduce the average case communication \ncomplexity. In particular, we show that the efficiency of our voting algorithm can be improved\nby choosing the parameters of the error correcting code to match the probability of\nthe computational faults. For example, consider an NMR system with 31 modules,\neach with a state of m bits, where each module has an independent computational\nerror probability of 10 to the power of minus 3. In this NMR system, our algorithm can reduce the average case communication complexity to approximately 1.0825m compared with the \ncommunication complexity of 31m of the naive algorithm in which every module broadcasts\nits local result to all other modules. We have also implemented the voting algorithm\nover a network of workstations. The experimental performance results match well the\ntheoretical predictions.", "date": "1996-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1996.ETR011", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1996.ETR011", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr011.pdf", "url": "https://authors.library.caltech.edu/records/34cns-m4519/files/etr011.pdf" }, "related_objects": [ { "basename": "etr011.ps", "url": "https://authors.library.caltech.edu/records/34cns-m4519/files/etr011.ps" } ], "pub_year": "1996", "author_list": "Xu, Lihao and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/t5axy-4xq58", "eprint_id": 26065, "eprint_status": "archive", "datestamp": "2023-08-20 07:05:48", "lastmod": "2023-10-24 16:12:50", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Gibson-M-A", "name": { "family": "Gibson", "given": "Michael A." } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Efficient Digital to Analog Encoding", "ispublished": "unpub", "full_text_status": "public", "abstract": "NOTE: Text or symbols not renderable in plain ASCII are indicated by [...]. Abstract included in .pdf document.\n\n\nAn important issue in analog circuit design is the problem of digital to analog conversion,\nnamely, the encoding of Boolean variables into a single analog value which contains enough\ninformation to reconstruct the values of the Boolean variables. A natural question is: What\nis the complexity of implementing the digital to analog encoding function? That question was\nrecently answered in (5), where matching lower and upper bounds on the size of the circuit for\nthe encoding function were proven. In particular, it was proven that [...] 2-input arithmetic\ngates are necessary and sufficient for implementing the encoding function of n Boolean variables.\nHowever, the proof of the upper bound is not constructive.\n\nIn this paper, we present an explicit construction of a digital to analog encoder that is\noptimal in the number of 2-input arithmetic gates. In addition, we present an efficient analog\nto digital decoding algorithm. Namely, given the encoded analog value, our decoding algorithm\nreconstructs the original Boolean values. Our construction is suboptimal in that it uses constants\n[...] bits.", "date": "1996-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1996.ETR009", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1996.ETR009", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr009.pdf", "url": "https://authors.library.caltech.edu/records/t5axy-4xq58/files/etr009.pdf" }, "related_objects": [ { "basename": "etr009.ps", "url": "https://authors.library.caltech.edu/records/t5axy-4xq58/files/etr009.ps" } ], "pub_year": "1996", "author_list": "Gibson, Michael A. and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/npa6y-nyj57", "eprint_id": 26064, "eprint_status": "archive", "datestamp": "2023-08-20 07:05:42", "lastmod": "2023-10-24 16:12:48", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Bohossian-V", "name": { "family": "Bohossian", "given": "Vasken" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Multiple Threshold Neural Logic", "ispublished": "unpub", "full_text_status": "public", "abstract": "We introduce a new Boolean computing element, related to the Boolean version of a\nneural element. Instead of the sign function in the Boolean neural element, (also known\nas an LT element), it computes an arbitrary (with polynomialy many transitions) Boolean\nfunction of the weighted sum of its inputs. We call the new computing element an LTM\nelement, which stands for Linear Threshold with Multiple transitions.\nThe paper consists of the following main contributions related to our study of LTM\ncircuits: (i) the characterization of the computing power of LTM relative to LT circuits,\n(ii) a proof that the area of the VLSI layout, is reduced from O(n to the power of 2) in LT circuits to O(n) in LTM circuits, for n inputs symmetric Boolean functions, and (iii) the creation of efficient\ndesigns of LTM circuits for the addition of a multiple number of integers and the product,\nof two integers. In particular, we show how to compute the addition of m integers with a\nsingle layer of LTM elements.", "date": "1996-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1996.ETR010", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1996.ETR010", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr010.pdf", "url": "https://authors.library.caltech.edu/records/npa6y-nyj57/files/etr010.pdf" }, "related_objects": [ { "basename": "etr010.ps", "url": "https://authors.library.caltech.edu/records/npa6y-nyj57/files/etr010.ps" } ], "pub_year": "1996", "author_list": "Bohossian, Vasken and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/1g70n-67892", "eprint_id": 26062, "eprint_status": "archive", "datestamp": "2023-08-20 07:05:31", "lastmod": "2023-10-24 16:12:43", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Blaum-M", "name": { "family": "Blaum", "given": "Mario" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" }, { "id": "Pifarre-G-E", "name": { "family": "Pifarre", "given": "Gustavo ED." } }, { "id": "Sanz-J-L-C", "name": { "family": "Sanz", "given": "Jorge L. C." } } ] }, "title": "On Optimal Placements of Processors in Tori Networks", "ispublished": "unpub", "full_text_status": "public", "abstract": "Two and three dimensional k-tori are among the most used topologies in the design of new\nparallel computers. Traditionally (with the exception of the Tera parallel computer), these\nnetworks have been used as fully-populated networks, in the sense that every routing node\nin the topology is subjected to message injection. However, fully-populated tori and meshes\nexhibit a theoretical throughput which degrades as the network size increases. In addition,\nthe performance of those networks is sensitive to link faults. In contrast, multistage networks\n(that are partially populated) scale well with the network size. We propose to add slackness in\nfully-populated tori by reducing the number of processors and we study optimal fault-tolerant\nrouting strategies for the resulting interconnections.\nThe key concept that we study is the average link load in an interconnection network with\na given placement and a routing algorithm, where a placement is the subset of the nodes in the\ninterconnection network that are attached to processors. Reducing the load on the links by the\nchoice of a placement and a routing algorithm leads to improvements in both the performance\nand the fault tolerance of the communication system.\nOur main contribution is the construction of optimal placements for 2 and 3-dimensional\nk-tori networks and their corresponding routing algorithms. Those placements yield a linear (in\nthe number of processors) link load and are of optimal size.", "date": "1996-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1996.ETR012", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1996.ETR012", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr012.pdf", "url": "https://authors.library.caltech.edu/records/1g70n-67892/files/etr012.pdf" }, "related_objects": [ { "basename": "etr012.ps", "url": "https://authors.library.caltech.edu/records/1g70n-67892/files/etr012.ps" } ], "pub_year": "1996", "author_list": "Blaum, Mario; Bruck, Jehoshua; et el." }, { "id": "https://authors.library.caltech.edu/records/098qk-57131", "eprint_id": 26060, "eprint_status": "archive", "datestamp": "2023-08-20 07:05:19", "lastmod": "2023-10-24 16:12:39", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Fan-C-C", "name": { "family": "Fan", "given": "Charles C." } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Optimal Constructions of Fault-Tolerant Multistage Interconnection Networks", "ispublished": "unpub", "full_text_status": "public", "abstract": "In this paper we discover the family of Fault-Tolerant Multistage Interconnection Networks\n(MINs) that tolerates switch faults with a minimal number of redundant switching stages.\nWhile previously known constructions handled switch faults by eliminating complete stages,\nour approach is to bypass faulty switches by utilizing redundant paths. As a result, we\nare able to construct the first known fault-tolerant MINs that are optimal in the number\nof redundant stages. Our fault model assumes that a faulty switch can be bypassed and\nour goal is to guarantee arbitrary point to point and broadcast connectivity. Under this\nmodel, we show that to tolerate f switch faults the MIN must have at least f redundant\nstages. We then present the explicit construction of a MIN that meets this lower-bound.\nThis construction repeatedly uses the singleton basis of the n-dimensional vector space as the\nmask vectors of the MIN. We generalize this construction and prove that an n-dimensional\nMIN is optimally fault-tolerant if and only if the mask vectors of every n consecutive stages\nspan the n-dimensional vector space.", "date": "1996-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1996.ETR014", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1996.ETR014", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr014.pdf", "url": "https://authors.library.caltech.edu/records/098qk-57131/files/etr014.pdf" }, "related_objects": [ { "basename": "etr014.ps", "url": "https://authors.library.caltech.edu/records/098qk-57131/files/etr014.ps" } ], "pub_year": "1996", "author_list": "Fan, Charles C. and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/7w58g-man58", "eprint_id": 26068, "eprint_status": "archive", "datestamp": "2023-08-20 05:22:14", "lastmod": "2023-10-24 16:12:57", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Ziv-A", "name": { "family": "Ziv", "given": "Avi" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "An Online Algorithm for Checkpointing Placement", "ispublished": "unpub", "full_text_status": "public", "abstract": "Checkpointing is a common technique for reducing the\ntime to recover from faults in computer systems. By saving\nintermediate states of programs in a reliable storage, \ncheck pointing enables to reduce the lost processing time caused\nby faults. The length of the intervals between checkpoints\naffects the execution time of programs. Long intervals lead\nto long re-processing time, while too frequent checkpoint-\niizg leads to high checkpointing overhead. In this paper we\npresent an on-line algorithm for placement of checkpoints.\nThe algorithm uses on-line knowledge of the current cost\nof a checkpoint when it decides whether or not to place a\ncheckpoint. We show how the execution time of a program\nusing this algorithm can be analyzed. The total overhead of\nthe execution time when the proposed algorithm is used is\nsmaller than the overhead when fixed intervals are used. \nAlthough the proposed algorithm uses only on-line knowledge\nabout the cost of checkpointing, its behavior is close to the off-line optimal algorithm that uses a complete knowledge\nof checkpointing cost.", "date": "1995-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1995.ETR006", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1995.ETR006", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr006.ps", "url": "https://authors.library.caltech.edu/records/7w58g-man58/files/etr006.ps" }, "related_objects": [ { "basename": "etr006.pdf", "url": "https://authors.library.caltech.edu/records/7w58g-man58/files/etr006.pdf" } ], "pub_year": "1995", "author_list": "Ziv, Avi and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/1fv46-acs93", "eprint_id": 26067, "eprint_status": "archive", "datestamp": "2023-08-20 05:22:08", "lastmod": "2023-10-24 16:12:54", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" }, { "id": "Ho-C-T", "name": { "family": "Ho", "given": "Ching-Tien" } } ] }, "title": "Fault-Tolerant Cube Graphs and Coding Theory", "ispublished": "unpub", "full_text_status": "public", "abstract": "Hypercubes, meshes, tori and Omega networks are well known interconnection \nnetworks for parallel computers. The structure of those graphs can be described in a\nmore general framework called cube graphs. The idea is to assume that every node in\na graph with q to the power of l (letter l) nodes is represented by a unique string of l (letter l) symbols over GF(q). The edges are specified by a set of offsets, those are vectors of length l (letter l) over GF(q), where the two endpoints of an edge are an offset apart. We study techniques for tolerating edge faults in cube graphs that are based on adding redundant edges. The redundant\ngraph has the property that the structure of the original graph can be maintained\nin the presence of edge faults. Our main contribution is a technique for adding the\nredundant edges that utilizes constructions of error-correcting codes and generalizes\nexisting ad-hoc techniques.", "date": "1995-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1995.ETR007", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1995.ETR007", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr007.pdf", "url": "https://authors.library.caltech.edu/records/1fv46-acs93/files/etr007.pdf" }, "related_objects": [ { "basename": "etr007.ps", "url": "https://authors.library.caltech.edu/records/1fv46-acs93/files/etr007.ps" } ], "pub_year": "1995", "author_list": "Bruck, Jehoshua and Ho, Ching-Tien" }, { "id": "https://authors.library.caltech.edu/records/h144c-x3927", "eprint_id": 26066, "eprint_status": "archive", "datestamp": "2023-08-20 05:22:02", "lastmod": "2023-10-24 16:12:52", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Blaum-M", "name": { "family": "Blaum", "given": "Mario" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Interleaving Schemes for Multidimensional Cluster Errors", "ispublished": "unpub", "full_text_status": "public", "abstract": "We present 2 and 3-dimensional interleaving techniques for correcting 2 and 3-\ndimensional bursts (or clusters) of errors, where a cluster of errors is characterized by its\narea or volume. A recent application of correction of 2-dimensional clusters appeared\nin the context of holographic storage. Our main contribution is the construction of\nefficient 2 and 3-dimensional interleaving schemes. The schemes are based on arrays of\nintegers with the property that every connected component of area or volume t consists\nof distinct integers (we call these t-interleaved arrays). In the 2-dimensional case, our\nconstructions are optimal in the sense that they contain the smallest possible number\nof distinct integers, hence minimizing the number of codes required in an interleaving\nscheme.", "date": "1995-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1995.ETR008", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1995.ETR008", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr008.pdf", "url": "https://authors.library.caltech.edu/records/h144c-x3927/files/etr008.pdf" }, "related_objects": [ { "basename": "etr008.ps", "url": "https://authors.library.caltech.edu/records/h144c-x3927/files/etr008.ps" } ], "pub_year": "1995", "author_list": "Blaum, Mario and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/xx8aa-yck89", "eprint_id": 26069, "eprint_status": "archive", "datestamp": "2023-08-20 05:22:20", "lastmod": "2023-10-24 16:12:59", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Bohossian-V", "name": { "family": "Bohossian", "given": "Vasken" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "On Neural Networks with Minimal Weights", "ispublished": "unpub", "full_text_status": "public", "abstract": "Linear threshold elements are the basic building blocks of artificial\nneural networks. A linear threshold element computes a function\nthat is a sign of a weighted sum of the input variables. The weights\nare arbitrary integers: actually, they can be very big integers-\nexponential in the number of the input variables. However, in\npractice, it is difficult to implement big weights. In the present\nliterature a distinction is made between the two extreme cases:\nlinear threshold functions with polynomial-size weights as opposed\nto those with exponential-size weights. The main contribution of\nthis paper is to fill up the gap by further refining that separation.\nNamely, we prove that the class of linear threshold functions with\npolynomial-size weights can be divided into subclasses according\nto the degree of the polynomial. In fact we prove a more general\nresult-that there exists a minimal weight linear threshold function\nfor any arbitrary number of inputs and any weight size. To prove\nthose results we have developed a novel technique for constructing\nlinear threshold functions with minimal weights.", "date": "1995-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1995.ETR005", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1995.ETR005", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr005.pdf", "url": "https://authors.library.caltech.edu/records/xx8aa-yck89/files/etr005.pdf" }, "related_objects": [ { "basename": "etr005.ps", "url": "https://authors.library.caltech.edu/records/xx8aa-yck89/files/etr005.ps" } ], "pub_year": "1995", "author_list": "Bohossian, Vasken and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/aqapz-4np57", "eprint_id": 26071, "eprint_status": "archive", "datestamp": "2023-08-20 03:49:28", "lastmod": "2023-10-24 16:13:03", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Ziv-A", "name": { "family": "Ziv", "given": "Avi" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Analysis of Checkpointing Schemes for Multiprocessor Systems", "ispublished": "unpub", "full_text_status": "public", "abstract": "Parallel computing systems provide hardware redundancy that helps to achieve low cost fault-\ntolerance. Fault-tolerance is achieved, in those systems, by duplicating the task into more than one\nprocessor, and comparing the states of the processors at checkpoints. Many schemes that achieve\nfault tolerance exist, and most of them use checkpointing to reduce the time spent retrying a task.\nPerformance evaluation for most of the schemes either relies on simulation results, or uses a simplified\nfault model.\nThis paper suggests a novel technique, based on a Markov Reward Model (MRM), for analyzing the\nperformance of checkpointing schemes for fault-tolerance. We show how this technique can be used to\nderive the average execution time of a task and other important parameters related to the performance\nof checkpointing schemes. Our analytical results match well the values we obtained using a simulation\nprogram.\nWe compare the average task completion time and total work of four checkpointing schemes, TMR,\nDMR-B-2, DMR-F-1 and RFCS. We show that generally increasing the number of processors reduces\nthe average completion time, but increases the total work done by the processors. Namely, the TMR\nscheme, which uses three processors, is the quickest but does the most work, while the DMR-B-2 scheme,\nwhich uses only two processors, is the slowest of the four schemes but does the least work. However,\nin cases where there is a big difference between the time it takes to perform different operations, those\nresults can change. For example, when we assume that the schemes are implemented on workstations\nconnected by a LAN and the time to move data between workstations is relatively long, the DMR-B-2\nscheme can become quicker than the TMR scheme.", "date": "1994-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1994.ETR003", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1994.ETR003", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr003.pdf", "url": "https://authors.library.caltech.edu/records/aqapz-4np57/files/etr003.pdf" }, "related_objects": [ { "basename": "etr003.ps", "url": "https://authors.library.caltech.edu/records/aqapz-4np57/files/etr003.ps" } ], "pub_year": "1994", "author_list": "Ziv, Avi and Bruck, Jehoshua" }, { "id": "https://authors.library.caltech.edu/records/nc7m6-vay05", "eprint_id": 26073, "eprint_status": "archive", "datestamp": "2023-08-20 03:49:39", "lastmod": "2023-10-24 16:13:07", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" }, { "id": "Cypher-R", "name": { "family": "Cypher", "given": "Robert" } }, { "id": "Ho-C-T", "name": { "family": "Ho", "given": "Ching-Tien" } } ] }, "title": "Fault-Tolerant Meshes with Small Degree", "ispublished": "unpub", "full_text_status": "public", "abstract": "This paper presents constructions for fault-tolerant two-dimensional mesh \narchitectures. The constructions are designed to tolerate k faults while maintaining a healthy n\nby n mesh as a subgraph. They utilize several novel techniques for obtaining trade-offs\nbetween the number of spare nodes and the degree of the fault-tolerant network.\nWe consider both worst-case and random fault distributions. In terms of worst-case faults, we give a construction that has constant degree and O(k to the power of 3) spare nodes. This is\nthe first construction known in which the degree is constant and the number of spare\nnodes is independent of n. In terms of random faults, we present several new degree-6\nand degree-8 constructions and show (both analytically and through simulations) that\nthey can tolerate large numbers of randomly placed faults.", "date": "1994-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1994.ETR001", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1994.ETR001", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr001.pdf", "url": "https://authors.library.caltech.edu/records/nc7m6-vay05/files/etr001.pdf" }, "related_objects": [ { "basename": "etr001.ps", "url": "https://authors.library.caltech.edu/records/nc7m6-vay05/files/etr001.ps" } ], "pub_year": "1994", "author_list": "Bruck, Jehoshua; Cypher, Robert; et el." }, { "id": "https://authors.library.caltech.edu/records/j8hc8-cfd93", "eprint_id": 26070, "eprint_status": "archive", "datestamp": "2023-08-20 03:49:22", "lastmod": "2023-10-24 16:13:01", "type": "monograph", "metadata_visibility": "show", "creators": { "items": [ { "id": "Ziv-A", "name": { "family": "Ziv", "given": "Avi" } }, { "id": "Bruck-J", "name": { "family": "Bruck", "given": "Jehoshua" }, "orcid": "0000-0001-8474-0812" } ] }, "title": "Performance Optimization of Checkpointing Schemes with Task Duplication", "ispublished": "unpub", "full_text_status": "public", "abstract": "Checkpointing schemes enable fault-tolerant parallel and distributed computing by leveraging\nthe redundancy in hardware and software resources. In these systems, checkpointing serves two\npurposes: it helps in detecting faults by comparing the processors states at checkpoints, and\nit facilitates the reduction of fault recovery time by supplying a safe point to rollback to. The\nefficiency of checkpointing schemes is influenced by the time it takes to perform the comparisons\nand to store the states. The fact that checkpoints consist of both storing of states and comparison\nbetween states, with conflicting objectives regarding the frequency of those operations, limits\nthe performance of current checkpointing schemes.\nIn this paper we show that by tuning the checkpointing schemes to a given architecture, a\nsignificant reduction in the execution time can be achieved. We will present both analytical\nresults and experimental results that were obtained on a cluster of workstations and a parallel\ncomputer.\nThe main idea is to use two types of checkpoints: compare-checkpoints (comparing the states\nof the redundant processes to detect faults) and store-checkpoints (storing the states to reduce\nrecovery time). With two types of checkpoints, we can use both the comparison and storage\noperations in an efficient way and improve the performance of checkpointing schemes. As a\nparticular example of this approach we analyzed the DMR checkpointing scheme with store\nand compare checkpoints on two types of architectures, one where the comparison time is much\nhigher than the store time (like a cluster of workstations connected by a LAN) and one where the\nstore time is much higher than the comparison time (like the Intel Paragon supercomputer). We\nhave implemented a prototype of the new DMR schemes and run it on workstations connected by\na LAN and on the Intel Paragon supercomputer. The experimental results we obtained match\nthe analytical results and show that in some cases the overhead of the DMR checkpointing\nschemes on both architectures can be improved by as much as 40%.", "date": "1994-01-01", "date_type": "published", "publisher": "California Institute of Technology", "id_number": "CaltechPARADISE:1994.ETR004", "official_url": "https://resolver.caltech.edu/CaltechPARADISE:1994.ETR004", "rights": "You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.", "local_group": { "items": [ { "id": "Parallel-and-Distributed-Systems-Group" } ] }, "primary_object": { "basename": "etr004.pdf", "url": "https://authors.library.caltech.edu/records/j8hc8-cfd93/files/etr004.pdf" }, "related_objects": [ { "basename": "etr004.ps", "url": "https://authors.library.caltech.edu/records/j8hc8-cfd93/files/etr004.ps" } ], "pub_year": "1994", "author_list": "Ziv, Avi and Bruck, Jehoshua" } ]