Invariant Causal Set Covering Machines

TL;DR

This paper introduces Invariant Causal Set Covering Machines, a rule-based model that reliably identifies causal features by avoiding spurious correlations, with proven theoretical guarantees and empirical validation.

Contribution

It extends the Set Covering Machine algorithm to incorporate invariance principles, enabling causal feature selection in polynomial time.

Findings

Successfully identifies causal parents of variables.

Provably avoids spurious associations.

Operates efficiently in polynomial time.

Abstract

Rule-based models, such as decision trees, appeal to practitioners due to their interpretable nature. However, the learning algorithms that produce such models are often vulnerable to spurious associations and thus, they are not guaranteed to extract causally-relevant insights. In this work, we build on ideas from the invariant causal prediction literature to propose Invariant Causal Set Covering Machines, an extension of the classical Set Covering Machine algorithm for conjunctions/disjunctions of binary-valued rules that provably avoids spurious associations. We demonstrate both theoretically and empirically that our method can identify the causal parents of a variable of interest in polynomial time.