Probabilistic Reasoning Across the Causal Hierarchy

Abstract

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.

Cite

Text

Ibeling and Icard. "Probabilistic Reasoning Across the Causal Hierarchy." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I06.6577

Markdown

[Ibeling and Icard. "Probabilistic Reasoning Across the Causal Hierarchy." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/ibeling2020aaai-probabilistic/) doi:10.1609/AAAI.V34I06.6577

BibTeX

@inproceedings{ibeling2020aaai-probabilistic,
  title     = {{Probabilistic Reasoning Across the Causal Hierarchy}},
  author    = {Ibeling, Duligur and Icard, Thomas},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {10170-10177},
  doi       = {10.1609/AAAI.V34I06.6577},
  url       = {https://mlanthology.org/aaai/2020/ibeling2020aaai-probabilistic/}
}