Algorithms for Causal Reasoning in Probability Trees

Probability trees are one of the simplest models of causal generative processes. They possess clean semantics and -- unlike causal Bayesian networks -- they can represent context-specific causal dependencies, which are necessary for e.g. causal induction. Yet, they have received little attention from the AI and ML community. Here we present concrete algorithms for causal reasoning in discrete probability trees that cover the entire causal hierarchy (association, intervention, and counterfactuals), and operate on arbitrary propositional and causal events. Our work expands the domain of causal reasoning to a very general class of discrete stochastic processes.

[1]  J. Neumann,et al.  Theory of Games and Economic Behavior. , 1945 .

[2]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[3]  Peter Øhrstrøm,et al.  Temporal logic - from ancient ideas to artificial intelligence , 2010, Studies in linguistics and philosophy.

[4]  Craig Boutilier,et al.  Context-Specific Independence in Bayesian Networks , 1996, UAI.

[5]  Glenn Shafer,et al.  The art of causal conjecture , 1996 .

[6]  A. Dawid.  Causal Inference without Counterfactuals , 2000 .

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

[8]  Michael H. Bowling,et al.  Regret Minimization in Games with Incomplete Information , 2007, NIPS.

[9]  Yoav Shoham,et al.  Essentials of Game Theory: A Concise Multidisciplinary Introduction , 2008, Essentials of Game Theory: A Concise Multidisciplinary Introduction.

[10]  Daniel A. Braun,et al.  A Minimum Relative Entropy Principle for Learning and Acting , 2008, J. Artif. Intell. Res..

[11]  Pedro A. Ortega.  Bayesian Causal Induction , 2011, NIPS 2011.

[12]  Elias Bareinboim,et al.  Bandits with Unobserved Confounders: A Causal Approach , 2015, NIPS.

[13]  Pedro A. Ortega.  Subjectivity, Bayesianism, and causality , 2014, Pattern Recognit. Lett..

[14]  A. Dawid,et al.  Statistical Causality from a Decision-Theoretic Perspective , 2014, 1405.2292.

[15]  Jim Q. Smith,et al.  A Differential Approach to Causality in Staged Trees , 2016, Probabilistic Graphical Models.

[16]  Tor Lattimore,et al.  Causal Bandits: Learning Good Interventions via Causal Inference , 2016, NIPS.

[17]  J. Pearl,et al.  Causal Inference in Statistics: A Primer , 2016 .

[18]  Matt J. Kusner,et al.  Counterfactual Fairness , 2017, NIPS.

[19]  Christiane Görgen.  An algebraic characterisation of staged trees : their geometry and causal implications , 2017 .

[20]  Elias Bareinboim,et al.  Fairness in Decision-Making - The Causal Explanation Formula , 2018, AAAI.

[21]  Jim Q. Smith,et al.  Equivalence classes of staged trees , 2015, Bernoulli.

[22]  S. Witty.  Causal Graphs vs. Causal Programs: The Case of Conditional Branching , 2018 .

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

[24]  Hongseok Yang,et al.  An Introduction to Probabilistic Programming , 2018, ArXiv.

[25]  Bernhard Scholkopf.  Causality for Machine Learning , 2019 .

[26]  David Lopez-Paz,et al.  Invariant Risk Minimization , 2019, ArXiv.

[27]  Silvia Chiappa,et al.  Path-Specific Counterfactual Fairness , 2018, AAAI.

[28]  Zeb Kurth-Nelson,et al.  Causal Reasoning from Meta-reinforcement Learning , 2019, ArXiv.

[29]  Shane Legg,et al.  Understanding Agent Incentives using Causal Influence Diagrams. Part I: Single Action Settings , 2019, ArXiv.

[30]  Shane Legg,et al.  The Incentives that Shape Behaviour , 2020, ArXiv.