Testing (Conditional) Mutual Information

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Seyfried, Jan, Sen, Sayantan, Tomamichel, Marco
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910986854727680
author Seyfried, Jan
Sen, Sayantan
Tomamichel, Marco
author_facet Seyfried, Jan
Sen, Sayantan
Tomamichel, Marco
contents We investigate the sample complexity of mutual information and conditional mutual information testing. For conditional mutual information testing, given access to independent samples of a triple of random variables $(A, B, C)$ with unknown distribution, we want to distinguish between two cases: (i) $A$ and $C$ are conditionally independent, i.e., $I(A\!:\!C|B) = 0$, and (ii) $A$ and $C$ are conditionally dependent, i.e., $I(A\!:\!C|B) \geq \varepsilon$ for some threshold $\varepsilon$. We establish an upper bound on the number of samples required to distinguish between the two cases with high confidence, as a function of $\varepsilon$ and the three alphabet sizes. We conjecture that our bound is tight and show that this is indeed the case in several parameter regimes. For the special case of mutual information testing (when $B$ is trivial), we establish the necessary and sufficient number of samples required up to polylogarithmic terms. Our technical contributions include a novel method to efficiently simulate weakly correlated samples from the conditionally independent distribution $P_{A|B} P_{C|B} P_B$ given access to samples from an unknown distribution $P_{ABC}$, and a new estimator for equivalence testing that can handle such correlated samples, which might be of independent interest.
format Preprint
id arxiv_https___arxiv_org_abs_2506_03894
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Testing (Conditional) Mutual Information
Seyfried, Jan
Sen, Sayantan
Tomamichel, Marco
Data Structures and Algorithms
Information Theory
We investigate the sample complexity of mutual information and conditional mutual information testing. For conditional mutual information testing, given access to independent samples of a triple of random variables $(A, B, C)$ with unknown distribution, we want to distinguish between two cases: (i) $A$ and $C$ are conditionally independent, i.e., $I(A\!:\!C|B) = 0$, and (ii) $A$ and $C$ are conditionally dependent, i.e., $I(A\!:\!C|B) \geq \varepsilon$ for some threshold $\varepsilon$. We establish an upper bound on the number of samples required to distinguish between the two cases with high confidence, as a function of $\varepsilon$ and the three alphabet sizes. We conjecture that our bound is tight and show that this is indeed the case in several parameter regimes. For the special case of mutual information testing (when $B$ is trivial), we establish the necessary and sufficient number of samples required up to polylogarithmic terms. Our technical contributions include a novel method to efficiently simulate weakly correlated samples from the conditionally independent distribution $P_{A|B} P_{C|B} P_B$ given access to samples from an unknown distribution $P_{ABC}$, and a new estimator for equivalence testing that can handle such correlated samples, which might be of independent interest.
title Testing (Conditional) Mutual Information
topic Data Structures and Algorithms
Information Theory
url https://arxiv.org/abs/2506.03894