Probabilistic Reasoning across the Causal Hierarchy
Probabilistic Reasoning across the Causal Hierarchy
复制标题
跨因果层次的概率推理
DOI：
10.1609/aaai.v34i06.6577
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Thomas F. Icard
中科院分区：
文献类型：
--
作者：
D. Ibeling;Thomas F. Icard
我们将关联、干预和反事实这三个层次的因果层级形式化为一系列概率逻辑语言。我们的语言表达能力严格递增，第一种能够表达定量概率推理——包括条件独立性和贝叶斯推理，第二种对因果效应进行do - 演算推理编码，第三种针对任意反事实查询捕捉一种完全表达性的do - 演算。我们给出了在结构因果模型和概率程序上都完备的相应的一系列有限公理化，并表明每种语言的可满足性和有效性在多项式空间内是可判定的。
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.