Enregistré dans:
Détails bibliographiques
Auteurs principaux: Auricchio, Gennaro, Toscani, Giuseppe
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2510.09123
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911201875722240
author Auricchio, Gennaro
Toscani, Giuseppe
author_facet Auricchio, Gennaro
Toscani, Giuseppe
contents We study the rate of convergence to equilibrium of the solutions to Fokker-Planck type equations with linear drift by means of Cramér and Energy distances, which have been recently widely used in problems related to AI, in particular for tasks related to machine learning. In all cases in which the Fokker-Planck type equations can be treated through these distances, it is shown that the rate of decay is improved with respect to known results which are based on the decay of relative entropy.
format Preprint
id arxiv_https___arxiv_org_abs_2510_09123
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Energy distance and evolution problems: a promising tool for kinetic equations
Auricchio, Gennaro
Toscani, Giuseppe
Analysis of PDEs
Physics and Society
We study the rate of convergence to equilibrium of the solutions to Fokker-Planck type equations with linear drift by means of Cramér and Energy distances, which have been recently widely used in problems related to AI, in particular for tasks related to machine learning. In all cases in which the Fokker-Planck type equations can be treated through these distances, it is shown that the rate of decay is improved with respect to known results which are based on the decay of relative entropy.
title Energy distance and evolution problems: a promising tool for kinetic equations
topic Analysis of PDEs
Physics and Society
url https://arxiv.org/abs/2510.09123