Regularity theory and geometry of unbalanced optimal transport
Not on the map. Why?
Abstract (arXiv)
Using the dual formulation only, we show that the regularity of unbalanced optimal transport also called entropy-transport inherits from the regularity of standard optimal transport. We provide detailed examples of Riemannian manifolds and costs for which unbalanced optimal transport is regular.Among all entropy-transport formulations, Wasserstein-Fisher-Rao (WFR) metric, also called Hellinger-Kantorovich, stands out since it admits a dynamic formulation, which extends the Benamou-Brenier formulation of optimal transport. After demonstrating the equivalence between dynamic and static formulations on a closed Riemannian manifold, we prove a polar factorization theorem, similar to the one due to Brenier and Mc-Cann. As a byproduct, we formulate the Monge-Amp`ere equation associated with WFR metric, which also holds for more general costs. Last, we study the link between c-convex functions for the cost induced by the WFR metric and the cost on the cone. The main result is that the weak Ma-Trudinger-Wang condition on the cone implies the same condition on the manifold for the cost induced by WFR.
Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Dec 2021.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2023: 2; 2024: 2; 2025: 2.
6 papers.
- 2023Generative Modeling through the Semi-dual Formulation of Unbalanced Optimal Transportcited by 41
- 2024Scalable Wasserstein Gradient Flow for Generative Modeling through Unbalanced Optimal Transportcited by 23
- 2024Improving Neural Optimal Transport via Displacement Interpolationcited by 7
- 2023A High-Quality Robust Diffusion Framework for Corrupted Datasetcited by 6
- 2025Taming Flow Matching with Unbalanced Optimal Transport into Fast Pansharpeningcited by 6
- 2025Reweighted Flow Matching via Unbalanced OT for Label-free Long-tailed Generationcited by 1
- 2025Reweighted Flow Matching via Unbalanced OT for Label-free Long-tailed Generation30 Sep 2025
- 2025Taming Flow Matching with Unbalanced Optimal Transport into Fast Pansharpening19 Mar 2025
- 2024Improving Neural Optimal Transport via Displacement Interpolation3 Oct 2024
- 2024Scalable Wasserstein Gradient Flow for Generative Modeling through Unbalanced Optimal Transport8 Feb 2024
- 2023A High-Quality Robust Diffusion Framework for Corrupted Dataset28 Nov 2023
- 2023Generative Modeling through the Semi-dual Formulation of Unbalanced Optimal Transport24 May 2023