Entropic regularization of Monge's problem

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Nutz, Marcel, Zhong, Chenyang
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908996763385856
author Nutz, Marcel
Zhong, Chenyang
author_facet Nutz, Marcel
Zhong, Chenyang
contents We study the vanishing-regularization limit of entropically regularized optimal transport (EOT) for the Euclidean distance cost $c(x,y)=\|x-y\|$ in dimension $d>1$. We develop a comprehensive variational convergence framework that entails two main results. First, we resolve the longstanding entropic selection problem: the EOT minimizer converges to a distinguished optimal transport plan that is characterized explicitly as the solution of a constrained EOT problem on each transport ray. Denoting by $\varepsilon>0$ the regularization parameter, this selection holds for all $o(\varepsilon)$-approximate minimizers, with sharp failure at the $O(\varepsilon)$ scale. Second, we establish an explicit second-order expansion of the entropic transport cost. The second-order term encodes the geometry of the regularization and reveals the optimal asymptotic tradeoff between entropy and transport cost.
format Preprint
id arxiv_https___arxiv_org_abs_2604_21578
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Entropic regularization of Monge's problem
Nutz, Marcel
Zhong, Chenyang
Optimization and Control
Analysis of PDEs
Functional Analysis
Probability
We study the vanishing-regularization limit of entropically regularized optimal transport (EOT) for the Euclidean distance cost $c(x,y)=\|x-y\|$ in dimension $d>1$. We develop a comprehensive variational convergence framework that entails two main results. First, we resolve the longstanding entropic selection problem: the EOT minimizer converges to a distinguished optimal transport plan that is characterized explicitly as the solution of a constrained EOT problem on each transport ray. Denoting by $\varepsilon>0$ the regularization parameter, this selection holds for all $o(\varepsilon)$-approximate minimizers, with sharp failure at the $O(\varepsilon)$ scale. Second, we establish an explicit second-order expansion of the entropic transport cost. The second-order term encodes the geometry of the regularization and reveals the optimal asymptotic tradeoff between entropy and transport cost.
title Entropic regularization of Monge's problem
topic Optimization and Control
Analysis of PDEs
Functional Analysis
Probability
url https://arxiv.org/abs/2604.21578