Optimal Transport losses and Sinkhorn algorithm with general convex regularization

arXiv2007.00976MaRDI QIDQ6344264FDOQ6344264

Authors: Simone Di Marino, Augusto Gerolin 

Publication date: 2 July 2020

Abstract: We introduce a new class of convex-regularized Optimal Transport losses, which generalizes the classical Entropy-regularization of Optimal Transport and Sinkhorn divergences, and propose a generalized Sinkhorn algorithm. Our framework unifies many regularizations and numerical methods previously appeared in the literature. We show the existence of the maximizer for the dual problem, complementary slackness conditions, providing a complete characterization of solutions for such class of variational problems. As a consequence, we study structural properties of these losses, including continuity, differentiability and provide explicit formulas for the its gradient. Finally, we provide theoretical guarantees of convergences and stability of the generalized Sinkhorn algorithm, even in the continuous setting. The techniques developed here are directly applicable also to study Wasserstein barycenters or, more generally, multi-marginal problems.

This page was built for publication: Optimal Transport losses and Sinkhorn algorithm with general convex regularization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6344264)