Sample complexity for divergence regularized optimal transport with radial cost

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Han, Ruiyu, Wiesel, Johannes
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908902472286208
author Han, Ruiyu
Wiesel, Johannes
author_facet Han, Ruiyu
Wiesel, Johannes
contents We prove a new sample complexity result for divergence regularized optimal transport. Our bound holds for probability measures on~$\mathbb{R}^d$ with exponential tail decay and for radial cost functions that satisfy a local Lipschitz condition. It is sharp up to logarithmic factors, and captures the intrinsic dimension of the marginal distributions through a generalized covering number of their supports. Examples that fit into our framework include subexponential and subgaussian distributions and radial cost functions $c(x,y)=|x-y|^p$ for $p\ge 1$ with logarithmic entropy or polynomial $α$-divergence.
format Preprint
id arxiv_https___arxiv_org_abs_2510_05685
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sample complexity for divergence regularized optimal transport with radial cost
Han, Ruiyu
Wiesel, Johannes
Statistics Theory
Probability
We prove a new sample complexity result for divergence regularized optimal transport. Our bound holds for probability measures on~$\mathbb{R}^d$ with exponential tail decay and for radial cost functions that satisfy a local Lipschitz condition. It is sharp up to logarithmic factors, and captures the intrinsic dimension of the marginal distributions through a generalized covering number of their supports. Examples that fit into our framework include subexponential and subgaussian distributions and radial cost functions $c(x,y)=|x-y|^p$ for $p\ge 1$ with logarithmic entropy or polynomial $α$-divergence.
title Sample complexity for divergence regularized optimal transport with radial cost
topic Statistics Theory
Probability
url https://arxiv.org/abs/2510.05685