A Quantitative Entropy Power Inequality for Dependent Random Vectors

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Madiman, Mokshay, Melbourne, James, Roberto, Cyril
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911331767025664
author Madiman, Mokshay
Melbourne, James
Roberto, Cyril
author_facet Madiman, Mokshay
Melbourne, James
Roberto, Cyril
contents The entropy power inequality for independent random vectors is a foundational result of information theory, with deep connections to probability and geometric functional analysis. Several extensions of the entropy power inequality have been developed for settings with dependence, including by Takano, Johnson, and Rioul. We extend these works by developing a quantitative version of the entropy power inequality for dependent random vectors. A notable consequence is that an entropy power inequality stated using conditional entropies holds for random vectors whose joint density is log-supermodular.
format Preprint
id arxiv_https___arxiv_org_abs_2512_19002
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Quantitative Entropy Power Inequality for Dependent Random Vectors
Madiman, Mokshay
Melbourne, James
Roberto, Cyril
Information Theory
Probability
The entropy power inequality for independent random vectors is a foundational result of information theory, with deep connections to probability and geometric functional analysis. Several extensions of the entropy power inequality have been developed for settings with dependence, including by Takano, Johnson, and Rioul. We extend these works by developing a quantitative version of the entropy power inequality for dependent random vectors. A notable consequence is that an entropy power inequality stated using conditional entropies holds for random vectors whose joint density is log-supermodular.
title A Quantitative Entropy Power Inequality for Dependent Random Vectors
topic Information Theory
Probability
url https://arxiv.org/abs/2512.19002