On the Complexity of Counterfactual Reasoning

TL;DR

This paper analyzes the computational complexity of counterfactual reasoning in structural causal models, showing it is no harder than associational or interventional reasoning under certain frameworks, with implications for tractability.

Contribution

It establishes bounds linking the complexity of counterfactual reasoning to that of associational and interventional reasoning using treewidth concepts.

Findings

Counterfactual reasoning complexity is bounded by associational/interventional reasoning.

Counterfactual reasoning is tractable if associational/interventional reasoning is tractable.

Empirical results show the complexity gap on random SCMs.

Abstract

We study the computational complexity of counterfactual reasoning in relation to the complexity of associational and interventional reasoning on structural causal models (SCMs). We show that counterfactual reasoning is no harder than associational or interventional reasoning on fully specified SCMs in the context of two computational frameworks. The first framework is based on the notion of treewidth and includes the classical variable elimination and jointree algorithms. The second framework is based on the more recent and refined notion of causal treewidth which is directed towards models with functional dependencies such as SCMs. Our results are constructive and based on bounding the (causal) treewidth of twin networks -- used in standard counterfactual reasoning that contemplates two worlds, real and imaginary -- to the (causal) treewidth of the underlying SCM structure. In particular, we show that the latter (causal) treewidth is no more than twice the former plus one. Hence, if associational or interventional reasoning is tractable on a fully specified SCM then counterfactual reasoning is tractable too. We extend our results to general counterfactual reasoning that requires contemplating more than two worlds and discuss applications of our results to counterfactual reasoning with a partially specified SCM that is coupled with data. We finally present empirical results that measure the gap between the complexities of counterfactual reasoning and associational/interventional reasoning on random SCMs.