Journal article 440 views 22 downloads
Some inequalities on Riemannian manifolds linking Entropy, Fisher information, Stein discrepancy and Wasserstein distance
Journal of Functional Analysis, Volume: 285, Issue: 5, Start page: 109997
Swansea University Author: Feng-yu Wang
-
PDF | Accepted Manuscript
Distributed under the terms of a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND 4.0).
Download (234.66KB)
DOI (Published version): 10.1016/j.jfa.2023.109997
Abstract
For a complete connected Riemannian manifold M let V ∈ C2(M) be such that μ(dx) =e−V(x) vol(dx) is a probability measure on M. Taking μ as reference measure, we derive in-equalities for probability measures on M linking relative entropy, Fisher information, Steindiscrepancy and Wasserstein distance....
Published in: | Journal of Functional Analysis |
---|---|
ISSN: | 0022-1236 |
Published: |
Elsevier BV
2023
|
Online Access: |
Check full text
|
URI: | https://cronfa.swan.ac.uk/Record/cronfa63390 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Abstract: |
For a complete connected Riemannian manifold M let V ∈ C2(M) be such that μ(dx) =e−V(x) vol(dx) is a probability measure on M. Taking μ as reference measure, we derive in-equalities for probability measures on M linking relative entropy, Fisher information, Steindiscrepancy and Wasserstein distance. These inequalities strengthen in particular the fa-mous log-Sobolev and transportation-cost inequality and extend the so-called Entropy/Stein-discrepancy/Information (HSI) inequality established by Ledoux, Nourdin and Peccati (2015)for the standard Gaussian measure on Euclidean space to the setting of Riemannian manifolds. |
---|---|
Keywords: |
Relative entropy, Fisher information, Stein discrepancy, Wasserstein distance |
College: |
Faculty of Science and Engineering |
Issue: |
5 |
Start Page: |
109997 |