Convergence rates for regularized unbalanced optimal transport: the discrete case
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912624862560256 |
|---|---|
| author | Nenna, Luca Pegon, Paul Tocquec, Louis |
| author_facet | Nenna, Luca Pegon, Paul Tocquec, Louis |
| contents | Unbalanced optimal transport (UOT) is a natural extension of optimal transport (OT) allowing comparison between measures of different masses. It arises naturally in machine learning by offering a robustness against outliers. The aim of this work is to provide convergence rates of the regularized transport cost and plans towards their original solution when both measures are weighted sums of Dirac masses. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_07917 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Convergence rates for regularized unbalanced optimal transport: the discrete case Nenna, Luca Pegon, Paul Tocquec, Louis Optimization and Control Numerical Analysis Primary: 49Q22, Secondary: 49N15, 94A17 Unbalanced optimal transport (UOT) is a natural extension of optimal transport (OT) allowing comparison between measures of different masses. It arises naturally in machine learning by offering a robustness against outliers. The aim of this work is to provide convergence rates of the regularized transport cost and plans towards their original solution when both measures are weighted sums of Dirac masses. |
| title | Convergence rates for regularized unbalanced optimal transport: the discrete case |
| topic | Optimization and Control Numerical Analysis Primary: 49Q22, Secondary: 49N15, 94A17 |
| url | https://arxiv.org/abs/2507.07917 |