Conditional Independence Testing for Discrete Distributions: Beyond $\chi^2$- and $G$-tests

TL;DR

This paper advances conditional independence testing for discrete data by developing practical, non-Poissonized tests with optimality guarantees, demonstrating classical tests are sub-optimal in high dimensions, and providing an R package for implementation.

Contribution

It introduces a practical, optimality-guaranteed conditional independence test that overcomes limitations of previous methods relying on Poissonization.

Findings

Classical $oldsymbol{ ext{chi}^2}$- and $G$-tests are sub-optimal in high-dimensional settings.

Proposed tests are calibrated with Monte Carlo permutations for better practical performance.

The paper provides an R package implementing the new tests.

Abstract

This paper is concerned with the problem of conditional independence testing for discrete data. In recent years, researchers have shed new light on this fundamental problem, emphasizing finite-sample optimality. The non-asymptotic viewpoint adapted in these works has led to novel conditional independence tests that enjoy certain optimality under various regimes. Despite their attractive theoretical properties, the considered tests are not necessarily practical, relying on a Poissonization trick and unspecified constants in their critical values. In this work, we attempt to bridge the gap between theory and practice by reproving optimality without Poissonization and calibrating tests using Monte Carlo permutations. Along the way, we also prove that classical asymptotic $\chi^2$- and $G$-tests are notably sub-optimal in a high-dimensional regime, which justifies the demand for new tools. Our theoretical results are complemented by experiments on both simulated and real-world datasets. Accompanying this paper is an R package UCI that implements the proposed tests.