Salvato in:
| Autori principali: | , , |
|---|---|
| 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 |