Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Stéphanovitch, Arthur
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2411.10235
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912385714880512
author Stéphanovitch, Arthur
author_facet Stéphanovitch, Arthur
contents We extend the classical regularity theory of optimal transport to non-optimal transport maps generated by heat flow for perturbations of Gaussian measures. Considering probability measures of the form $dμ(x) = \exp\left(-\frac{|x|^2}{2} + a(x)\right)dx$ on $\mathbb{R}^d$ where $a$ has Hölder regularity $C^β$ with $β\geq 0$; we show that the Langevin map transporting the $d$-dimensional Gaussian distribution onto $μ$ achieves Hölder regularity $C^{β+ 1}$, up to a logarithmic factor. We additionally present applications of this result to functional inequalities and generative modelling.
format Preprint
id arxiv_https___arxiv_org_abs_2411_10235
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Smooth transport map via diffusion process
Stéphanovitch, Arthur
Probability
We extend the classical regularity theory of optimal transport to non-optimal transport maps generated by heat flow for perturbations of Gaussian measures. Considering probability measures of the form $dμ(x) = \exp\left(-\frac{|x|^2}{2} + a(x)\right)dx$ on $\mathbb{R}^d$ where $a$ has Hölder regularity $C^β$ with $β\geq 0$; we show that the Langevin map transporting the $d$-dimensional Gaussian distribution onto $μ$ achieves Hölder regularity $C^{β+ 1}$, up to a logarithmic factor. We additionally present applications of this result to functional inequalities and generative modelling.
title Smooth transport map via diffusion process
topic Probability
url https://arxiv.org/abs/2411.10235