LOAIJan 9, 2020

Probabilistic Reasoning across the Causal Hierarchy

arXiv:2001.02889v535 citations
AI Analysis

This work provides a foundational framework for causal reasoning, enabling formal analysis across different levels of causal inference.

The authors formalized the three-tier causal hierarchy (association, intervention, counterfactuals) as probabilistic logical languages with increasing expressivity, showing that satisfiability and validity for each language are decidable in polynomial space.

We propose a formalization of the three-tier causal hierarchy of association, intervention, and counterfactuals as a series of probabilistic logical languages. Our languages are of strictly increasing expressivity, the first capable of expressing quantitative probabilistic reasoning -- including conditional independence and Bayesian inference -- the second encoding do-calculus reasoning for causal effects, and the third capturing a fully expressive do-calculus for arbitrary counterfactual queries. We give a corresponding series of finitary axiomatizations complete over both structural causal models and probabilistic programs, and show that satisfiability and validity for each language are decidable in polynomial space.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes