Year: 2023
Type: preprint
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.
Source: arXiv (Cornell University)
Language: English
Subfield: Applied Mathematics
Field: Mathematics
Domain: Physical Sciences
Open Access status: green
Awards: Development of a Foundation for Numerical Operator Algebras and its Applications, Geometry of optimal transport theory and gradient flows, Mathematical and numerical analysis of Sobolev gradient flows appearing in interface and materials science, Development of a foundation for discrete complex analysis, Robust and Efficient Numerical Methods for Matrix Problems with Singularity, Study on curvatures from the viewpoint of new convexities and its application to geometric analysis, G8211505071, Singularity analysis of complex functions for describing complex phenomena
OpenAlex ID: W4386977534