Closed Forms for Gaussian Kullback--Leibler Unbalanced Optimal Transport without Coupling Entropy

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Jiaping, Zhang, Yunxin
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910188691259392
author Yang, Jiaping
Zhang, Yunxin
author_facet Yang, Jiaping
Zhang, Yunxin
contents We obtain an explicit solution for the static Kullback--Leibler (KL) unbalanced optimal transport problem between finite non-degenerate Gaussian measures with quadratic cost, two independent positive marginal relaxation parameters, and no entropy penalty on the coupling. The minimizer is a scaled Wasserstein coupling between two adjusted Gaussian marginals and is supported on an affine graph; in entropic Gaussian unbalanced transport, by contrast, the optimal plan is non-degenerate on the product space. The covariance map is the unique positive definite solution of a Riccati equation and admits a principal-square-root representation. Compared with the known equal-penalty Gaussian Hellinger--Kantorovich endpoint, the result treats the asymmetric two-sided Kullback--Leibler relaxation and gives the modified marginals, joint minimizer, value, and a direct quadratic KL-dual certificate. The large-relaxation limit recovers the Gaussian Wasserstein cost for equal masses.
format Preprint
id arxiv_https___arxiv_org_abs_2605_02497
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Closed Forms for Gaussian Kullback--Leibler Unbalanced Optimal Transport without Coupling Entropy
Yang, Jiaping
Zhang, Yunxin
Optimization and Control
We obtain an explicit solution for the static Kullback--Leibler (KL) unbalanced optimal transport problem between finite non-degenerate Gaussian measures with quadratic cost, two independent positive marginal relaxation parameters, and no entropy penalty on the coupling. The minimizer is a scaled Wasserstein coupling between two adjusted Gaussian marginals and is supported on an affine graph; in entropic Gaussian unbalanced transport, by contrast, the optimal plan is non-degenerate on the product space. The covariance map is the unique positive definite solution of a Riccati equation and admits a principal-square-root representation. Compared with the known equal-penalty Gaussian Hellinger--Kantorovich endpoint, the result treats the asymmetric two-sided Kullback--Leibler relaxation and gives the modified marginals, joint minimizer, value, and a direct quadratic KL-dual certificate. The large-relaxation limit recovers the Gaussian Wasserstein cost for equal masses.
title Closed Forms for Gaussian Kullback--Leibler Unbalanced Optimal Transport without Coupling Entropy
topic Optimization and Control
url https://arxiv.org/abs/2605.02497