On the global convergence of Wasserstein gradient flow of the Coulomb discrepancy - Signal and communications Access content directly
Preprints, Working Papers, ... (Preprint) Year : 2023

On the global convergence of Wasserstein gradient flow of the Coulomb discrepancy

Abstract

In this work, we study the Wasserstein gradient flow of the Riesz energy defined on the space of probability measures. The Riesz kernels define a quadratic functional on the space of measure which is not in general geodesically convex in the Wasserstein geometry, therefore one cannot conclude to global convergence of the Wasserstein gradient flow using standard arguments. Our main result is the exponential convergence of the flow to the minimizer on a closed Riemannian manifold under the condition that the logarithm of the source and target measures are Hölder continuous. To this goal, we first prove that the Polyak-Lojasiewicz inequality is satisfied for sufficiently regular solutions. The key regularity result is the global in-time existence of Hölder solutions if the initial and target data are Hölder continuous, proven either in Euclidean space or on a closed Riemannian manifold. For general measures, we prove using flow interchange techniques that there is no local minima other than the global one for the Coulomb kernel. In fact, we prove that a Lagrangian critical point of the functional for the Coulomb (or Energy distance) kernel is equal to the target everywhere except on singular sets with empty interior. In addition, singular enough measures cannot be critical points.
Fichier principal
Vignette du fichier
OnGlobalConvergenceMMDFlows.pdf (360.75 Ko) Télécharger le fichier
main.pdf (391.77 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04282762 , version 1 (20-11-2023)
hal-04282762 , version 2 (26-01-2024)

Identifiers

Cite

Siwan Boufadène, François-Xavier Vialard. On the global convergence of Wasserstein gradient flow of the Coulomb discrepancy. 2023. ⟨hal-04282762v1⟩

Collections

LIGM_SIGNAL
222 View
250 Download

Altmetric

Share

Gmail Facebook X LinkedIn More