Salvato in:
Dettagli Bibliografici
Autori principali: Morikuni, Keiichi, Sakakibara, Koya, Takatsu, Asuka
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2309.11666
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916679520354304
author Morikuni, Keiichi
Sakakibara, Koya
Takatsu, Asuka
author_facet Morikuni, Keiichi
Sakakibara, Koya
Takatsu, Asuka
contents Regularization by the Shannon entropy enables us to efficiently and approximately solve optimal transport problems on a finite set. This paper is concerned with regularized optimal transport problems via Bregman divergence. We introduce the required properties for Bregman divergences, provide a non-asymptotic error estimate for the regularized problem, and show that the error estimate becomes faster than exponentially.
format Preprint
id arxiv_https___arxiv_org_abs_2309_11666
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Error estimate for regularized optimal transport problems via Bregman divergence
Morikuni, Keiichi
Sakakibara, Koya
Takatsu, Asuka
Optimization and Control
Numerical Analysis
52A41, 90C05, 65K10
Regularization by the Shannon entropy enables us to efficiently and approximately solve optimal transport problems on a finite set. This paper is concerned with regularized optimal transport problems via Bregman divergence. We introduce the required properties for Bregman divergences, provide a non-asymptotic error estimate for the regularized problem, and show that the error estimate becomes faster than exponentially.
title Error estimate for regularized optimal transport problems via Bregman divergence
topic Optimization and Control
Numerical Analysis
52A41, 90C05, 65K10
url https://arxiv.org/abs/2309.11666