An Asymptotic Test for Conditional Independence using Analytic Kernel Embeddings
Machine Learning
2022-06-17 v2 Machine Learning
Abstract
We propose a new conditional dependence measure and a statistical test for conditional independence. The measure is based on the difference between analytic kernel embeddings of two well-suited distributions evaluated at a finite set of locations. We obtain its asymptotic distribution under the null hypothesis of conditional independence and design a consistent statistical test from it. We conduct a series of experiments showing that our new test outperforms state-of-the-art methods both in terms of type-I and type-II errors even in the high dimensional setting.
Cite
@article{arxiv.2110.14868,
title = {An Asymptotic Test for Conditional Independence using Analytic Kernel Embeddings},
author = {Meyer Scetbon and Laurent Meunier and Yaniv Romano},
journal= {arXiv preprint arXiv:2110.14868},
year = {2022}
}