Error Probability Bounds for Invariant Causal Prediction via Multiple Access Channels

TL;DR

This paper establishes lower bounds on the error probability in invariant causal prediction by linking it to multiple access channel theory, providing new insights and bounds for causal discovery methods.

Contribution

It introduces a novel connection between invariant causal prediction and multiple access channels, leading to new lower bounds on error probability under various assumptions.

Findings

Derived three types of error probability bounds

Evaluated bounds against existing causal discovery methods

Proposed a heuristic based on minimum distance decoding

Abstract

We consider the problem of lower bounding the error probability under the invariant causal prediction (ICP) framework. To this end, we examine and draw connections between ICP and the zero-rate Gaussian multiple access channel by first proposing a variant of the original invariant prediction assumption, and then considering a special case of the Gaussian multiple access channel where a codebook is shared between an unknown number of senders. This connection allows us to develop three types of lower bounds on the error probability, each with different assumptions and constraints, leveraging techniques for multiple access channels. The proposed bounds are evaluated with respect to existing causal discovery methods as well as a proposed heuristic method based on minimum distance decoding.