Salvato in:
Dettagli Bibliografici
Autori principali: Xu, Yewei, Li, Qin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.13260
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914093245399040
author Xu, Yewei
Li, Qin
author_facet Xu, Yewei
Li, Qin
contents Wasserstein gradient flows have become a central tool for optimization problems over probability measures. A natural numerical approach is forward-Euler time discretization. We show, however, that even in the simple case where the energy functional is the Kullback-Leibler (KL) divergence against a smooth target density, forward-Euler can fail dramatically: the scheme does not converge to the gradient flow, despite the fact that the first variation $\nabla\frac{δF}{δρ}$ remains formally well defined at every step. We identify the root cause as a loss of regularity induced by the discretization, and prove that a suitable regularization of the functional restores the necessary smoothness, making forward-Euler a viable solver that converges in discrete time to the global minimizer.
format Preprint
id arxiv_https___arxiv_org_abs_2509_13260
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Forward Euler for Wasserstein Gradient Flows: Breakdown and Regularization
Xu, Yewei
Li, Qin
Numerical Analysis
Optimization and Control
65J20, 35Q49
Wasserstein gradient flows have become a central tool for optimization problems over probability measures. A natural numerical approach is forward-Euler time discretization. We show, however, that even in the simple case where the energy functional is the Kullback-Leibler (KL) divergence against a smooth target density, forward-Euler can fail dramatically: the scheme does not converge to the gradient flow, despite the fact that the first variation $\nabla\frac{δF}{δρ}$ remains formally well defined at every step. We identify the root cause as a loss of regularity induced by the discretization, and prove that a suitable regularization of the functional restores the necessary smoothness, making forward-Euler a viable solver that converges in discrete time to the global minimizer.
title Forward Euler for Wasserstein Gradient Flows: Breakdown and Regularization
topic Numerical Analysis
Optimization and Control
65J20, 35Q49
url https://arxiv.org/abs/2509.13260