Energy distance and evolution problems: a promising tool for kinetic equations
Analysis of PDEs
2025-10-13 v1 Physics and Society
Abstract
We study the rate of convergence to equilibrium of the solutions to Fokker-Planck type equations with linear drift by means of Cram\'er 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.
Cite
@article{arxiv.2510.09123,
title = {Energy distance and evolution problems: a promising tool for kinetic equations},
author = {Gennaro Auricchio and Giuseppe Toscani},
journal= {arXiv preprint arXiv:2510.09123},
year = {2025}
}
Comments
13 pages