Saved in:
Bibliographic Details
Main Authors: Wang, Shuchan, Stavrou, Photios A., Skoglund, Mikael
Format: Preprint
Published: 2021
Subjects:
Online Access:https://arxiv.org/abs/2109.08430
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917707716231168
author Wang, Shuchan
Stavrou, Photios A.
Skoglund, Mikael
author_facet Wang, Shuchan
Stavrou, Photios A.
Skoglund, Mikael
contents In this paper, we study the connection between entropic optimal transport and entropy power inequality (EPI). First, we prove an HWI-type inequality making use of the infinitesimal displacement convexity of optimal transport map. Second, we derive two Talagrand-type inequalities using the saturation of EPI that corresponds to a numerical term in our expression. We evaluate for a wide variety of distributions this term whereas for Gaussian and i.i.d. Cauchy distributions this term is found in explicit form. We show that our results extend previous results of Gaussian Talagrand inequality for Sinkhorn distance to the strongly log-concave case.
format Preprint
id arxiv_https___arxiv_org_abs_2109_08430
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Generalized Talagrand Inequality for Sinkhorn Distance using Entropy Power Inequality
Wang, Shuchan
Stavrou, Photios A.
Skoglund, Mikael
Information Theory
Machine Learning
In this paper, we study the connection between entropic optimal transport and entropy power inequality (EPI). First, we prove an HWI-type inequality making use of the infinitesimal displacement convexity of optimal transport map. Second, we derive two Talagrand-type inequalities using the saturation of EPI that corresponds to a numerical term in our expression. We evaluate for a wide variety of distributions this term whereas for Gaussian and i.i.d. Cauchy distributions this term is found in explicit form. We show that our results extend previous results of Gaussian Talagrand inequality for Sinkhorn distance to the strongly log-concave case.
title Generalized Talagrand Inequality for Sinkhorn Distance using Entropy Power Inequality
topic Information Theory
Machine Learning
url https://arxiv.org/abs/2109.08430