PAC Learning of Causal Trees with Latent Variables

Learning causal probabilistic models with latent variables from observational and experimental data is an important problem. In this paper we present a polynomial-time al- gorithm that PAC-learns the structure and parameters of a rooted, tree-structured causal network of bounded degree where the internal nodes of the tree cannot be observed or manipulated. Our algorithm is the first of its kind to provably learn the structure and parameters of tree-structured causal models with latent internal variables from random examples and active experiments.

[1]  Marissa Connor,et al.  Generative causal explanations of black-box classifiers , 2020, NeurIPS.

[2]  Judea Pearl,et al.  The seven tools of causal inference, with reflections on machine learning , 2019, Commun. ACM.

[3]  Prasad Tadepalli.  Learning Causal Trees with Latent Variables via Controlled Experimentation , 2019 .

[4]  Mélanie Frappier,et al.  The Book of Why: The New Science of Cause and Effect , 2018, Science.

[5]  Jean Honorio,et al.  Learning Bayes networks using interventional path queries in polynomial time and sample complexity , 2017, ArXiv.

[6]  Karthikeyan Shanmugam,et al.  Experimental Design for Learning Causal Graphs with Latent Variables , 2017, NIPS.

[7]  Jonas Peters,et al.  Causal inference by using invariant prediction: identification and confidence intervals , 2015, 1501.01332.

[8]  Peter Bühlmann,et al.  Two optimal strategies for active learning of causal models from interventional data , 2012, Int. J. Approx. Reason..

[9]  Frederick Eberhardt,et al.  Discovering Cyclic Causal Models with Latent Variables: A General SAT-Based Procedure , 2013, UAI.

[10]  Thomas S. Richardson,et al.  Learning high-dimensional directed acyclic graphs with latent and selection variables , 2011, 1104.5617.

[11]  Tze-Yun Leong,et al.  Active Learning for Causal Bayesian Network Structure with Non-symmetrical Entropy , 2009, PAKDD.

[12]  Yangbo He,et al.  Active Learning of Causal Networks with Intervention Experiments and Optimal Designs , 2008 .

[13]  Kevin P. Murphy,et al.  Exact Bayesian structure learning from uncertain interventions , 2007, AISTATS.

[14]  Tomi Silander,et al.  A Simple Approach for Finding the Globally Optimal Bayesian Network Structure , 2006, UAI.

[15]  Prasad Tadepalli,et al.  Learning from Examples and Membership Queries with Structured Determinations , 1998, Machine Learning.

[16]  Sanjoy Dasgupta,et al.  The Sample Complexity of Learning Fixed-Structure Bayesian Networks , 1997, Machine Learning.

[17]  Tom Burr,et al.  Causation, Prediction, and Search , 2003, Technometrics.

[18]  Daphne Koller,et al.  Active Learning for Structure in Bayesian Networks , 2001, IJCAI.

[19]  Gregory F. Cooper,et al.  Causal Discovery from a Mixture of Experimental and Observational Data , 1999, UAI.

[20]  Lisa Hellerstein,et al.  Learning Boolean Read-Once Formulas over Generalized Bases , 1995, J. Comput. Syst. Sci..

[21]  Prasad Tadepalli,et al.  Learning from Queries and Examples with Tree-structured Bias , 1993, ICML.

[22]  David Haussler,et al.  Decision Theoretic Generalizations of the PAC Model for Neural Net and Other Learning Applications , 1992, Inf. Comput..

[23]  Robert E. Schapire,et al.  Learning probabilistic read-once formulas on product distributions , 1991, COLT '91.

[24]  Leonard Pitt,et al.  Prediction-Preserving Reducibility , 1990, J. Comput. Syst. Sci..

[25]  Robert E. Schapire,et al.  Efficient distribution-free learning of probabilistic concepts , 1990, Proceedings [1990] 31st Annual Symposium on Foundations of Computer Science.

[26]  Leslie G. Valiant,et al.  Computational limitations on learning from examples , 1988, JACM.

[27]  Dana Angluin,et al.  Queries and concept learning , 1988, Machine Learning.

[28]  O. Penrose.  The Direction of Time , 1962 .

[29]  J. Lamperti.  ON CONVERGENCE OF STOCHASTIC PROCESSES , 1962 .

[30]  Illtyd Trethowan.  Causality , 1938 .