An Entropy Power Inequality for Dependent Variables

Simple item page
dc.contributor.authorMadiman, Mokshay
dc.contributor.authorMelbourne, James
dc.contributor.authorRoberto, Cyril
dc.date.accessioned2024-05-15T18:35:49Z
dc.date.available2024-05-15T18:35:49Z
dc.date.issued2024-04-05
dc.descriptionThis article was originally published in IEEE Transactions on Information Theory. The version of record is available at: https://doi.org/10.1109/TIT.2024.3385728. © 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. This article will be embargoed until 04/05/2026.
dc.description.abstractThe entropy power inequality for independent random variables is a foundational result of information theory, with deep connections to probability and geometric functional analysis. Very few extensions of the entropy power inequality have been developed for settings with dependence. We address this gap in the literature by developing entropy power inequalities for dependent random variables. In particular, we highlight the role of log-supermodularity in delivering sufficient conditions for an entropy power inequality stated using conditional entropies.
dc.description.sponsorshipResearch supported by the Labex MME-DII funded by ANR, reference ANR-11-LBX-0023-01, the Fondation Simone et Cino del Duca and the FP2M federation (CNRS FR 2036).
dc.identifier.citationM. Madiman, J. Melbourne and C. Roberto, "An Entropy Power Inequality for Dependent Variables," in IEEE Transactions on Information Theory, doi: 10.1109/TIT.2024.3385728.
dc.identifier.issn1557-9654
dc.identifier.urihttps://udspace.udel.edu/handle/19716/34408
dc.language.isoen_US
dc.publisherIEEE Transactions on Information Theory
dc.subjectEntropy Power Inequality
dc.subjectDependent Variables
dc.subjectlog-supermodular
dc.subjectsubmodular functions
dc.subjectFisher information
dc.titleAn Entropy Power Inequality for Dependent Variables
dc.typeArticle

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
An Entropy Power Inequality for Dependent Variables.pdf
Size:
1.04 MB
Format:
Adobe Portable Document Format
Description:
Main article
Download

License bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.22 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Open Access Publications