Error estimate for regularized optimal transport problems via Bregman divergence
Optimization and Control
2025-04-10 v2 Numerical Analysis
Numerical Analysis
Abstract
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.
Cite
@article{arxiv.2309.11666,
title = {Error estimate for regularized optimal transport problems via Bregman divergence},
author = {Keiichi Morikuni and Koya Sakakibara and Asuka Takatsu},
journal= {arXiv preprint arXiv:2309.11666},
year = {2025}
}
Comments
21 pages, 3 figures