Salvato in:
Dettagli Bibliografici
Autori principali: Debouchage, Antoine, Wang, Xiaozhen, Ren, Zhenjie, Buet-Golfouse, Francois
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2605.11944
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917484892782592
author Debouchage, Antoine
Wang, Xiaozhen
Ren, Zhenjie
Buet-Golfouse, Francois
author_facet Debouchage, Antoine
Wang, Xiaozhen
Ren, Zhenjie
Buet-Golfouse, Francois
contents This paper addresses the practical challenge in Entropic Optimal Transport (EOT) where the underlying ground cost function is typically latent and unobserved. Rather than assuming a fixed geometric cost, we adopt a data-driven approach where a shared cost is revealed only through samples from a reference optimal coupling. The question is then: given samples from a reference optimal coupling, can we recover the optimal coupling for new marginals under the same latent cost? We introduce a generative transfer framework that recovers the optimal coupling for new marginals by utilizing an iterative path-wise tilting algorithm. Unlike static importance reweighting, this method evolves the coupling jointly with a marginal transport path, allowing mass to move beyond the reference support. We derive sample-level learning rules for these infinitesimal updates, which yield covariance-type evolution equations for the associated transport vector fields. By integrating this dynamics with Conditional Flow Matching (CFM), we produce a practical sampler for paired data. Finally, we provide theoretical guarantees establishing a global convergence rate of \mathcal{O}(δ), ensuring the generated coupling converges to the target EOT plan in W_1 distance.
format Preprint
id arxiv_https___arxiv_org_abs_2605_11944
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Generative Transfer for Entropic Optimal Transport with Unknown Costs
Debouchage, Antoine
Wang, Xiaozhen
Ren, Zhenjie
Buet-Golfouse, Francois
Optimization and Control
This paper addresses the practical challenge in Entropic Optimal Transport (EOT) where the underlying ground cost function is typically latent and unobserved. Rather than assuming a fixed geometric cost, we adopt a data-driven approach where a shared cost is revealed only through samples from a reference optimal coupling. The question is then: given samples from a reference optimal coupling, can we recover the optimal coupling for new marginals under the same latent cost? We introduce a generative transfer framework that recovers the optimal coupling for new marginals by utilizing an iterative path-wise tilting algorithm. Unlike static importance reweighting, this method evolves the coupling jointly with a marginal transport path, allowing mass to move beyond the reference support. We derive sample-level learning rules for these infinitesimal updates, which yield covariance-type evolution equations for the associated transport vector fields. By integrating this dynamics with Conditional Flow Matching (CFM), we produce a practical sampler for paired data. Finally, we provide theoretical guarantees establishing a global convergence rate of \mathcal{O}(δ), ensuring the generated coupling converges to the target EOT plan in W_1 distance.
title Generative Transfer for Entropic Optimal Transport with Unknown Costs
topic Optimization and Control
url https://arxiv.org/abs/2605.11944