Wasserstein Gradient Flows for Moreau Envelopes of f-Divergences in Reproducing Kernel Hilbert Spaces

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Stein, Viktor, Neumayer, Sebastian, Rux, Nicolaj, Steidl, Gabriele
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913787792064512
author Stein, Viktor
Neumayer, Sebastian
Rux, Nicolaj
Steidl, Gabriele
author_facet Stein, Viktor
Neumayer, Sebastian
Rux, Nicolaj
Steidl, Gabriele
contents Commonly used $f$-divergences of measures, e.g., the Kullback-Leibler divergence, are subject to limitations regarding the support of the involved measures. A remedy is regularizing the $f$-divergence by a squared maximum mean discrepancy (MMD) associated with a characteristic kernel $K$. We use the kernel mean embedding to show that this regularization can be rewritten as the Moreau envelope of some function on the associated reproducing kernel Hilbert space. Then, we exploit well-known results on Moreau envelopes in Hilbert spaces to analyze the MMD-regularized $f$-divergences, particularly their gradients. Subsequently, we use our findings to analyze Wasserstein gradient flows of MMD-regularized $f$-divergences. We provide proof-of-the-concept numerical examples for flows starting from empirical measures. Here, we cover $f$-divergences with infinite and finite recession constants. Lastly, we extend our results to the tight variational formulation of $f$-divergences and numerically compare the resulting flows.
format Preprint
id arxiv_https___arxiv_org_abs_2402_04613
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Wasserstein Gradient Flows for Moreau Envelopes of f-Divergences in Reproducing Kernel Hilbert Spaces
Stein, Viktor
Neumayer, Sebastian
Rux, Nicolaj
Steidl, Gabriele
Machine Learning
Functional Analysis
Optimization and Control
46N10 (Primary) 46E22, 94A15 (Secondary)
Commonly used $f$-divergences of measures, e.g., the Kullback-Leibler divergence, are subject to limitations regarding the support of the involved measures. A remedy is regularizing the $f$-divergence by a squared maximum mean discrepancy (MMD) associated with a characteristic kernel $K$. We use the kernel mean embedding to show that this regularization can be rewritten as the Moreau envelope of some function on the associated reproducing kernel Hilbert space. Then, we exploit well-known results on Moreau envelopes in Hilbert spaces to analyze the MMD-regularized $f$-divergences, particularly their gradients. Subsequently, we use our findings to analyze Wasserstein gradient flows of MMD-regularized $f$-divergences. We provide proof-of-the-concept numerical examples for flows starting from empirical measures. Here, we cover $f$-divergences with infinite and finite recession constants. Lastly, we extend our results to the tight variational formulation of $f$-divergences and numerically compare the resulting flows.
title Wasserstein Gradient Flows for Moreau Envelopes of f-Divergences in Reproducing Kernel Hilbert Spaces
topic Machine Learning
Functional Analysis
Optimization and Control
46N10 (Primary) 46E22, 94A15 (Secondary)
url https://arxiv.org/abs/2402.04613