An Homogeneous Unbalanced Regularized Optimal Transport model with applications to Optimal Transport with Boundary
Not on the map. Why?
Abstract (arXiv)
This work studies how the introduction of the entropic regularization term in unbalanced Optimal Transport (OT) models may alter their homogeneity with respect to the input measures. We observe that in common settings (including balanced OT and unbalanced OT with Kullback-Leibler divergence to the marginals), although the optimal transport cost itself is not homogeneous, optimal transport plans and the so-called Sinkhorn divergences are indeed homogeneous. However, homogeneity does not hold in more general Unbalanced Regularized Optimal Transport (UROT) models, for instance those using the Total Variation as divergence to the marginals. We propose to modify the entropic regularization term to retrieve an UROT model that is homogeneous while preserving most properties of the standard UROT model. We showcase the importance of using our Homogeneous UROT (HUROT) model when it comes to regularize Optimal Transport with Boundary, a transportation model involving a spatially varying divergence to the marginals for which the standard (inhomogeneous) UROT model would yield inappropriate behavior.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 11 of its 25 references that are in the map. First posted on arXiv 6 Jan 2022.
Builds on
11 of 25 references.
References · 11
- 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
- 2018Computational Optimal Transportcited by 765
- 2017Learning Generative Models with Sinkhorn Divergencescited by 310
- 2017An introduction to Topological Data Analysis: fundamental and practical aspects for data scientistscited by 171
- 2015On Wasserstein Two Sample Testing and Related Families of Nonparametric Testscited by 165
- 2015Optimal Entropy-Transport problems and a new Hellinger-Kantorovich distance between positive measurescited by 138
- 2019Sinkhorn Divergences for Unbalanced Optimal Transportcited by 52
- 2020Debiased Sinkhorn barycenterscited by 34
- 2018Large Scale computation of Means and Clusters for Persistence Diagrams using Optimal Transportcited by 32
- 2019Understanding the Topology and the Geometry of the Space of Persistence Diagrams via Optimal Partial Transportcited by 17
- 2015Unbalanced Optimal Transport: Dynamic and Kantorovich Formulationcited by 6
Built on by
Citing papers per year: 2023: 1.
1 paper.