Computing Optimal Transport Plans via Min-Max Gradient Flows

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Conger, Lauren, Hoffmann, Franca, Baptista, Ricardo, Mazumdar, Eric
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915307039227904
author Conger, Lauren
Hoffmann, Franca
Baptista, Ricardo
Mazumdar, Eric
author_facet Conger, Lauren
Hoffmann, Franca
Baptista, Ricardo
Mazumdar, Eric
contents We pose the Kantorovich optimal transport problem as a min-max problem with a Nash equilibrium that can be obtained dynamically via a two-player game, providing a framework for approximating optimal couplings. We prove convergence of the timescale-separated gradient descent dynamics to the optimal transport plan, and implement the gradient descent algorithm with a particle method, where the marginal constraints are enforced weakly using the KL divergence, automatically selecting a dynamical adaptation of the regularizer. The numerical results highlight the different advantages of using the standard Kullback-Leibler (KL) divergence versus the reverse KL divergence with this approach, opening the door for new methodologies.
format Preprint
id arxiv_https___arxiv_org_abs_2504_16890
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Computing Optimal Transport Plans via Min-Max Gradient Flows
Conger, Lauren
Hoffmann, Franca
Baptista, Ricardo
Mazumdar, Eric
Optimization and Control
Analysis of PDEs
We pose the Kantorovich optimal transport problem as a min-max problem with a Nash equilibrium that can be obtained dynamically via a two-player game, providing a framework for approximating optimal couplings. We prove convergence of the timescale-separated gradient descent dynamics to the optimal transport plan, and implement the gradient descent algorithm with a particle method, where the marginal constraints are enforced weakly using the KL divergence, automatically selecting a dynamical adaptation of the regularizer. The numerical results highlight the different advantages of using the standard Kullback-Leibler (KL) divergence versus the reverse KL divergence with this approach, opening the door for new methodologies.
title Computing Optimal Transport Plans via Min-Max Gradient Flows
topic Optimization and Control
Analysis of PDEs
url https://arxiv.org/abs/2504.16890