CaltechAUTHORS: Combined
https://feeds.library.caltech.edu/people/Eberhardt-Frederick/combined.rss
A Caltech Library Repository Feedhttp://www.rssboard.org/rss-specificationpython-feedgenenFri, 06 Sep 2024 18:56:37 -0700Almost Optimal Intervention Sets for Causal Discovery
https://resolver.caltech.edu/CaltechAUTHORS:20190327-085859738
Year: 2008
DOI: 10.48550/arXiv.1206.3250
We conjecture that the worst case number of experiments necessary and sufficient to discover a causal graph uniquely given its observational Markov equivalence class can be specified as a function of the largest clique in the Markov equivalence class. We provide an algorithm that computes intervention sets that we believe are optimal for the above task. The algorithm builds on insights gained from the worst case analysis in Eberhardt et al. (2005) for sequences of experiments when all possible directed acyclic graphs over N variables are considered. A simulation suggests that our conjecture is correct. We also show that a generalization of our conjecture to other classes of possible graph hypotheses cannot be given easily, and in what sense the algorithm is then no longer optimal.https://resolver.caltech.edu/CaltechAUTHORS:20190327-085859738Noisy-OR Models with Latent Confounding
https://resolver.caltech.edu/CaltechAUTHORS:20190327-085849059
Year: 2011
DOI: 10.48550/arXiv.1202.3735v1
Given a set of experiments in which varying subsets of observed variables are subject to intervention, we consider the problem of identifiability of causal models exhibiting latent confounding. While identifiability is trivial when each experiment intervenes on a large number of variables, the situation is more complicated when only one or a few variables are subject to intervention per experiment. For linear causal models with latent variables Hyttinen et al. (2010) gave precise conditions for when such data are sufficient to identify the full model. While their result cannot be extended to discrete-valued variables with arbitrary cause-effect relationships, we show that a similar result can be obtained for the class of causal models whose conditional probability distributions are restricted to a 'noisy-OR' parameterization. We further show that identification is preserved under an extension of the model that allows for negative influences, and present learning algorithms that we test for accuracy, scalability and robustness.https://resolver.caltech.edu/CaltechAUTHORS:20190327-085849059On the number of experiments sufficient and in the worst case necessary to identify all causal relations among N variables
https://resolver.caltech.edu/CaltechAUTHORS:20190327-085852486
Year: 2012
DOI: 10.48550/arXiv.1207.1389
We show that if any number of variables are allowed to be simultaneously and independently randomized in any one experiment, log_2(N) + 1 experiments are sufficient and in the worst case necessary to determine the causal relations among N ≥ 2 variables when no latent variables, no sample selection bias and no feedback cycles are present. For all K, 0 < K < 1/2 N we provide an upper bound on the number experiments required to determine causal structure when each experiment simultaneously randomizes K variables. For large N, these bounds are significantly lower than the N - 1 bound required when each experiment randomizes at most one variable. For k_(max) < N/2, we show that (N/k_(max) -1) + N/2k_(max) log_2(k_(max)) experiments are sufficient and in the worst case necessary. We offer a conjecture as to the minimal number of experiments that are in the worst case sufficient to identify all causal relations among N observed variables that are a subset of the vertices of a DAG.https://resolver.caltech.edu/CaltechAUTHORS:20190327-085852486Causal discovery of linear cyclic models from multiple experimental data sets with overlapping variables
https://resolver.caltech.edu/CaltechAUTHORS:20190327-085855919
Year: 2012
DOI: 10.48550/arXiv.1210.4879
Much of scientific data is collected as randomized experiments intervening on some and observing other variables of interest. Quite often, a given phenomenon is investigated in several studies, and different sets of variables are involved in each study. In this article we consider the problem of integrating such knowledge, inferring as much as possible concerning the underlying causal structure with respect to the union of observed variables from such experimental or passive observational overlapping data sets. We do not assume acyclicity or joint causal sufficiency of the underlying data generating model, but we do restrict the causal relationships to be linear and use only second order statistics of the data. We derive conditions for full model identifiability in the most generic case, and provide novel techniques for incorporating an assumption of faithfulness to aid in inference. In each case we seek to establish what is and what is not determined by the data at hand.https://resolver.caltech.edu/CaltechAUTHORS:20190327-085855919Discovering cyclic causal models with latent variables: a general SAT-based procedure
https://resolver.caltech.edu/CaltechAUTHORS:20190327-085903347
Year: 2013
DOI: 10.48550/arXiv.1309.6836
We present a very general approach to learning the structure of causal models based on d-separation constraints, obtained from any given set of overlapping passive observational or experimental data sets. The procedure allows for both directed cycles (feedback loops) and the presence of latent variables. Our approach is based on a logical representation of causal pathways, which permits the integration of quite general background knowledge, and inference is performed using a Boolean satisfiability (SAT) solver. The procedure is complete in that it exhausts the available information on whether any given edge can be determined to be present or absent, and returns "unknown" otherwise. Many existing constraint-based causal discovery algorithms can be seen as special cases, tailored to circumstances in which one or more restricting assumptions apply. Simulations illustrate the effect of these assumptions on discovery and how the present algorithm scales.https://resolver.caltech.edu/CaltechAUTHORS:20190327-085903347Experiment Selection for Causal Discovery
https://resolver.caltech.edu/CaltechAUTHORS:20140123-114755984
Year: 2013
Randomized controlled experiments are often described as the most reliable tool available to scientists
for discovering causal relationships among quantities of interest. However, it is often unclear
how many and which different experiments are needed to identify the full (possibly cyclic) causal
structure among some given (possibly causally insufficient) set of variables. Recent results in the
causal discovery literature have explored various identifiability criteria that depend on the assumptions
one is able to make about the underlying causal process, but these criteria are not directly
constructive for selecting the optimal set of experiments. Fortunately, many of the needed constructions
already exist in the combinatorics literature, albeit under terminology which is unfamiliar to
most of the causal discovery community. In this paper we translate the theoretical results and apply
them to the concrete problem of experiment selection. For a variety of settings we give explicit
constructions of the optimal set of experiments and adapt some of the general combinatorics results
to answer questions relating to the problem of experiment selection.https://resolver.caltech.edu/CaltechAUTHORS:20140123-114755984Experimental Indistinguishability of Causal Structures
https://resolver.caltech.edu/CaltechAUTHORS:20140227-092549193
Year: 2013
DOI: 10.1086/673865
Using a variety of different results from the literature, I show how causal discovery with experiments is limited unless substantive assumptions about the underlying causal structure are made. These results undermine the view that experiments, such as randomized controlled trials, can independently provide a gold standard for causal discovery. Moreover, I present a concrete example in which causal underdetermination persists despite exhaustive experimentation and argue that such cases undermine the appeal of an interventionist account of causation as its dependence on other assumptions is not spelled out.https://resolver.caltech.edu/CaltechAUTHORS:20140227-092549193Direct Causes and the Trouble with Soft Interventions
https://resolver.caltech.edu/CaltechAUTHORS:20141023-135945304
Year: 2014
DOI: 10.1007/s10670-013-9552-2
An interventionist account of causation characterizes causal relations in terms of changes resulting from particular interventions. I provide a new example of a causal relation for which there does not exist an intervention satisfying the common interventionist standard. I consider adaptations that would save this standard and describe their implications for an interventionist account of causation. No adaptation preserves all the aspects that make the interventionist account appealing. Part of the fallout is a clearer account of the difficulties in characterizing so-called "soft" interventions.https://resolver.caltech.edu/CaltechAUTHORS:20141023-135945304Equidynamics and reliable reasoning about frequencies
https://resolver.caltech.edu/CaltechAUTHORS:20170616-075028154
Year: 2015
DOI: 10.1007/s11016-014-9971-y
Strevens' Tychomancy is an important book for philosophers and historians of science, and for scientists interested in the processes by which we reason about probabilities and frequencies, or interested in the evolution of our ability to do so. Strevens notes that we often have very good intuitions about probability and frequencies in physical processes, and asks how and why that is so. He describes several closely related reasoning strategies that would justify such intuitions. These "equidynamic" (xi) reasoning strategies1 can be used to infer, beginning from relatively minimal assumptions, conclusions about frequencies of outcomes of physical processes involving complex interactions. Strevens illustrates the strategies by applying them to examples such as Maxwell's derivation of an equilibrium probability distribution over states of a gas, physical games of chance and similar systems, and organisms interacting in evolving populations. Strevens argues that we routinely engage in these reasoning strategies, largely through unconscious processes that are in some sense innate.https://resolver.caltech.edu/CaltechAUTHORS:20170616-075028154Visual Causal Feature Learning
https://resolver.caltech.edu/CaltechAUTHORS:20190327-085913684
Year: 2015
DOI: 10.48550/arXiv.1412.2309
We provide a rigorous definition of the visual cause of a behavior that is broadly applicable to the visually driven behavior in humans, animals, neurons, robots and other perceiving systems. Our framework generalizes standard accounts of causal learning to settings in which the causal variables need to be constructed from micro-variables. We prove the Causal Coarsening Theorem, which allows us to gain causal knowledge from observational data with minimal experimental effort. The theorem provides a connection to standard inference techniques in machine learning that identify features of an image that correlate with, but may not cause, the target behavior. Finally, we propose an active learning scheme to learn a manipulator function that performs optimal manipulations on the image to automatically identify the visual cause of a target behavior. We illustrate our inference and learning algorithms in experiments based on both synthetic and real data.https://resolver.caltech.edu/CaltechAUTHORS:20190327-085913684Green and grue causal variables
https://resolver.caltech.edu/CaltechAUTHORS:20160602-123514680
Year: 2016
DOI: 10.1007/s11229-015-0832-z
The causal Bayes net framework specifies a set of axioms for causal discovery. This article explores the set of causal variables that function as relata in these axioms. Spirtes (2007) showed how a causal system can be equivalently described by two different sets of variables that stand in a non-trivial translation-relation to each other, suggesting that there is no "correct" set of causal variables. I extend Spirtes' result to the general framework of linear structural equation models and then explore to what extent the possibility to intervene or a preference for simpler causal systems may help in selecting among sets of causal variables.https://resolver.caltech.edu/CaltechAUTHORS:20160602-123514680Multi-Level Cause-Effect Systems
https://resolver.caltech.edu/CaltechAUTHORS:20190329-151702979
Year: 2016
DOI: 10.48550/arXiv.1512.07942
We present a domain-general account of causation that applies to settings in which macro-level causal relations between two systems are of interest, but the relevant causal features are poorly understood and have to be aggregated from vast arrays of micro-measurements. Our approach generalizes that of Chalupka et. al. (2015) to the setting in which the macro-level effect is not specified. We formalize the connection between micro- and macro-variables in such situations and provide a coherent framework describing causal relations at multiple levels of analysis. We present an algorithm that discovers macro-variable causes and effects from micro-level measurements obtained from an experiment. We further show how to design experiments to discover macro-variables from observational micro-variable data. Finally, we show that under specific conditions, one can identify multiple levels of causal structure. Throughout the article, we use a simulated neuroscience multi-unit recording experiment to illustrate the ideas and the algorithms.https://resolver.caltech.edu/CaltechAUTHORS:20190329-151702979Unsupervised Discovery of El Niño Using Causal Feature Learning on Microlevel Climate Data
https://resolver.caltech.edu/CaltechAUTHORS:20170530-090152140
Year: 2016
DOI: 10.48550/arXiv.1605.09370
We show that the climate phenomena of El Niño and La Niña arise naturally as states of macro-variables when our recent causal feature learning framework (Chalupka et al., 2015, 2016) is applied to micro-level measures of zonal wind (ZW) and sea surface temperatures (SST) taken over the equatorial band of the Pacific Ocean. The method identifies these unusual climate states on the basis of the relation between ZW and SST patterns without any input about past occurrences of El Niño or La Niña. The simpler alternatives of (i) clustering the SST fields while disregarding their relationship with ZW patterns, or (ii) clustering the joint ZW-SST patterns, do not discover El Niño. We discuss the degree to which our method supports a causal interpretation and use a low-dimensional toy example to explain its success over other clustering approaches. Finally, we propose a new robust and scalable alternative to our original algorithm (Chalupka et al., 2016), which circumvents the need for high-dimensional density learning.https://resolver.caltech.edu/CaltechAUTHORS:20170530-090152140Causal Discovery from Subsampled Time Series Data by Constraint Optimization
https://resolver.caltech.edu/CaltechAUTHORS:20170221-090923083
Year: 2016
DOI: 10.48550/arXiv.arXiv.1602.07970
PMCID: PMC5305170
This paper focuses on causal structure estimation from time series data in which measurements are obtained at a coarser timescale than the causal timescale of the underlying system. Previous work has shown that such subsampling can lead to significant errors about the system's causal structure if not properly taken into account. In this paper, we first consider the search for the system timescale causal structures that correspond to a given measurement timescale structure. We provide a constraint satisfaction procedure whose computational performance is several orders of magnitude better than previous approaches. We then consider finite-sample data as input, and propose the first constraint optimization approach for recovering the system timescale causal structure. This algorithm optimally recovers from possible conflicts due to statistical errors. More generally, these advances allow for a robust and non-parametric estimation of system timescale causal structures from subsampled time series data.https://resolver.caltech.edu/CaltechAUTHORS:20170221-090923083Causal Feature Learning: An Overview
https://resolver.caltech.edu/CaltechAUTHORS:20170530-090152248
Year: 2017
DOI: 10.1007/s41237-016-0008-2
Causal feature learning (CFL) (Chalupka et al., Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence. AUAI Press, Edinburgh, pp 181–190, 2015) is a causal inference framework rooted in the language of causal graphical models (Pearl J, Reasoning and inference. Cambridge University Press, Cambridge, 2009; Spirtes et al., Causation, Prediction, and Search. Massachusetts Institute of Technology, Massachusetts, 2000), and computational mechanics (Shalizi, PhD thesis, University of Wisconsin at Madison, 2001). CFL is aimed at discovering high-level causal relations from low-level data, and at reducing the experimental effort to understand confounding among the high-level variables. We first review the scientific motivation for CFL, then present a detailed introduction to the framework, laying out the definitions and algorithmic steps. A simple example illustrates the techniques involved in the learning steps and provides visual intuition. Finally, we discuss the limitations of the current framework and list a number of open problems.https://resolver.caltech.edu/CaltechAUTHORS:20170530-090152248A constraint optimization approach to causal discovery from subsampled time series data
https://resolver.caltech.edu/CaltechAUTHORS:20171109-074339105
Year: 2017
DOI: 10.1016/j.ijar.2017.07.009
We consider causal structure estimation from time series data in which measurements are obtained at a coarser timescale than the causal timescale of the underlying system. Previous work has shown that such subsampling can lead to significant errors about the system's causal structure if not properly taken into account. In this paper, we first consider the search for system timescale causal structures that correspond to a given measurement timescale structure. We provide a constraint satisfaction procedure whose computational performance is several orders of magnitude better than previous approaches. We then consider finite-sample data as input, and propose the first constraint optimization approach for recovering system timescale causal structure. This algorithm optimally recovers from possible conflicts due to statistical errors. We then apply the method to real-world data, investigate the robustness and scalability of our method, consider further approaches to reduce underdetermination in the output, and perform an extensive comparison between different solvers on this inference problem. Overall, these advances build towards a full understanding of non-parametric estimation of system timescale causal structures from subsampled time series data.https://resolver.caltech.edu/CaltechAUTHORS:20171109-074339105Fast Conditional Independence Test for Vector Variables with Large Sample Sizes
https://resolver.caltech.edu/CaltechAUTHORS:20180613-135346984
Year: 2018
DOI: 10.48550/arXiv.1804.02747
We present and evaluate the Fast (conditional) Independence Test (FIT) -- a nonparametric conditional independence test. The test is based on the idea that when P(X∣Y,Z)=P(X∣Y), Z is not useful as a feature to predict X, as long as Y is also a regressor. On the contrary, if P(X∣Y,Z)≠P(X∣Y), Z might improve prediction results. FIT applies to thousand-dimensional random variables with a hundred thousand samples in a fraction of the time required by alternative methods. We provide an extensive evaluation that compares FIT to six extant nonparametric independence tests. The evaluation shows that FIT has low probability of making both Type I and Type II errors compared to other tests, especially as the number of available samples grows. Our implementation of FIT is publicly available.https://resolver.caltech.edu/CaltechAUTHORS:20180613-135346984Estimating Causal Direction and Confounding of Two Discrete Variables
https://resolver.caltech.edu/CaltechAUTHORS:20190327-085917121
Year: 2019
DOI: 10.48550/arXiv.1611.01504
We propose a method to classify the causal relationship between two discrete variables given only the joint distribution of the variables, acknowledging that the method is subject to an inherent baseline error. We assume that the causal system is acyclicity, but we do allow for hidden common causes. Our algorithm presupposes that the probability distributions P(C) of a cause C is independent from the probability distribution P(E∣C) of the cause-effect mechanism. While our classifier is trained with a Bayesian assumption of flat hyperpriors, we do not make this assumption about our test data. This work connects to recent developments on the identifiability of causal models over continuous variables under the assumption of "independent mechanisms". Carefully-commented Python notebooks that reproduce all our experiments are available online at http://vision.caltech.edu/~kchalupk/code.html.https://resolver.caltech.edu/CaltechAUTHORS:20190327-085917121Approximate Causal Abstraction
https://resolver.caltech.edu/CaltechAUTHORS:20200527-100350364
Year: 2019
DOI: 10.48550/arXiv.1906.11583
Scientific models describe natural phenomena at different levels of abstraction. Abstract descriptions can provide the basis for interventions on the system and explanation of observed phenomena at a level of granularity that is coarser than the most fundamental account of the system. Beckers and Halpern (2019), building on prior work of Rubinstein et al. (2017), developed an account of abstraction for causal models that is exact. Here we extend this account to the more realistic case where an abstract causal model only offers an approximation of the underlying system. We show how the resulting account handles the discrepancy that can arise between low- and high-level causal models of the same system, and in the process provide an account of how one causal model approximates another, a topic of independent interest. Finally, we extend the account of approximate abstractions to probabilistic causal models, indicating how and where uncertainty can enter into an approximate abstraction.https://resolver.caltech.edu/CaltechAUTHORS:20200527-100350364ASP-based Discovery of Semi-Markovian Causal Models under Weaker Assumptions
https://resolver.caltech.edu/CaltechAUTHORS:20200527-101434154
Year: 2020
DOI: 10.48550/arXiv.1906.02385
In recent years the possibility of relaxing the so-called Faithfulness assumption in automated causal discovery has been investigated. The investigation showed (1) that the Faithfulness assumption can be weakened in various ways that in an important sense preserve its power, and (2) that weakening of Faithfulness may help to speed up methods based on Answer Set Programming. However, this line of work has so far only considered the discovery of causal models without latent variables. In this paper, we study weakenings of Faithfulness for constraint-based discovery of semi-Markovian causal models, which accommodate the possibility of latent variables, and show that both (1) and (2) remain the case in this more realistic setting.https://resolver.caltech.edu/CaltechAUTHORS:20200527-101434154Causal Mapping of Emotion Networks in the Human Brain: Framework and Initial Findings
https://resolver.caltech.edu/CaltechAUTHORS:20171115-073336929
Year: 2020
DOI: 10.1016/j.neuropsychologia.2017.11.015
PMCID: PMC5949245
Emotions involve many cortical and subcortical regions, prominently including the amygdala. It remains unknown how these multiple network components interact, and it remains unknown how they cause the behavioral, autonomic, and experiential effects of emotions. Here we describe a framework for combining a novel technique, concurrent electrical stimulation with fMRI (es-fMRI), together with a novel analysis, inferring causal structure from fMRI data (causal discovery). We outline a research program for investigating human emotion with these new tools, and provide initial findings from two large resting-state datasets as well as case studies in neurosurgical patients with electrical stimulation of the amygdala. The overarching goal is to use causal discovery methods on fMRI data to infer causal graphical models of how brain regions interact, and then to further constrain these models with direct stimulation of specific brain regions and concurrent fMRI. We conclude by discussing limitations and future extensions. The approach could yield anatomical hypotheses about brain connectivity, motivate rational strategies for treating mood disorders with deep brain stimulation, and could be extended to animal studies that use combined optogenetic fMRI.https://resolver.caltech.edu/CaltechAUTHORS:20171115-073336929Personality beyond taxonomy
https://resolver.caltech.edu/CaltechAUTHORS:20201109-135419046
Year: 2020
DOI: 10.1038/s41562-020-00989-3
Human and animal behaviour exhibits complex but regular patterns over time, often referred to as expressions of personality. Yet it remains unclear what personality really is: is it just the behavioural patterns themselves, something in the brain, in the genes or perhaps all of these? Here we offer a set of causal hypotheses about the role of personality, integrating psychological and neuroscientific approaches to personality in a testable framework. These hypotheses clarify the causal and constitutive relations that personality has with genes, environment, brain, mind and behaviour, and we suggest specific experiments that can adjudicate amongst the different hypotheses. We focus on a set of models that propose that personality is instantiated in the brain, distally caused by genes and environment and, in turn, causing the overt behaviours from which it is often inferred. We argue that articulating and testing such models will be essential in a mature science of personality.https://resolver.caltech.edu/CaltechAUTHORS:20201109-135419046Intracranial electrical stimulation alters meso-scale network integration as a function of network topology
https://resolver.caltech.edu/CaltechAUTHORS:20210831-204705170
Year: 2021
DOI: 10.1101/2021.01.16.426941
Human brain dynamics are organized into a multi-scale network structure that contains multiple tight-knit, meso-scale communities. Recent work has demonstrated that many psychological capacities, as well as impairments in cognitive function secondary to damage, can be mapped onto organizing principles at this mesoscopic scale. However, we still don't know the rules that govern the dynamic interactions between regions that are constrained by the topology of the broader network. In this preregistered study, we utilized a unique human dataset in which whole brain BOLD-fMRI activity was recorded simultaneously with intracranial electrical stimulation, to characterize the effects of direct neural stimulation on the dynamic reconfiguration of the broader network. Direct neural stimulation increased the extent to which the stimulation site's own mesoscale community integrated with the rest of the brain. Further, we found that these network changes depended on the topological role of the stimulation site itself: stimulating regions with high participation coefficients led to global integration, whereas stimulating sites with low participation coefficients integrated that regions' own community with the rest of the brain. These findings provide direct causal evidence for how network topology shapes and constrains inter-regional coordination, and suggest applications for targeted therapeutic interventions in patients with deep-brain stimulation.https://resolver.caltech.edu/CaltechAUTHORS:20210831-204705170A contemporary example of Reichenbachian coordination
https://resolver.caltech.edu/CaltechAUTHORS:20220315-626013000
Year: 2022
DOI: 10.1007/s11229-022-03571-8
This article is an attempt to provide an example that illustrates Hans Reichenbach's concept of coordination. Throughout Reichenbach's career the concept of coordination played an important role in his understanding of the connection between reality and how it is scientifically described. Reichenbach never fully specified what coordination is and how exactly it works. Instead, we are left with a variety of hints and gestures, many not entirely consistent with each other and several that are subject to change over the course of his career. Using the example of how to discover and construct causal variables, I will show that most of the features of coordination that Reichenbach described can be instantiated together and formulated precisely.https://resolver.caltech.edu/CaltechAUTHORS:20220315-626013000Causal Emergence: When Distortions in a Map Obscure the Territory
https://resolver.caltech.edu/CaltechAUTHORS:20220309-981595000
Year: 2022
DOI: 10.3390/philosophies7020030
We provide a critical assessment of the account of causal emergence presented in Erik Hoel's 2017 article "When the map is better than the territory". The account integrates causal and information theoretic concepts to explain under what circumstances there can be causal descriptions of a system at multiple scales of analysis. We show that the causal macro variables implied by this account result in interventions with significant ambiguity, and that the operations of marginalization and abstraction do not commute. Both of these are desiderata that, we argue, any account of multi-scale causal analysis should be sensitive to. The problems we highlight in Hoel's definition of causal emergence derive from the use of various averaging steps and the introduction of a maximum entropy distribution that is extraneous to the system under investigation.https://resolver.caltech.edu/CaltechAUTHORS:20220309-981595000