Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.05569 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911695742435328 |
|---|---|
| author | Selitskiy, Anton Millard, David |
| author_facet | Selitskiy, Anton Millard, David |
| contents | This paper shows that the semi-dual formulation of the optimal transport problem has a degenerate saddle-point structure, and that its numerical solution is equivalent to solving a constrained optimization problem. We derive necessary and sufficient conditions for the convergence of Monge maps without requiring optimality of the dual potential. This analysis helps explain why, in practice, numerical algorithms often require more iterations to update the transport map than the potential. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_05569 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Stability of the Monge Map in Semi-Dual Optimal Transport Selitskiy, Anton Millard, David Optimization and Control Machine Learning This paper shows that the semi-dual formulation of the optimal transport problem has a degenerate saddle-point structure, and that its numerical solution is equivalent to solving a constrained optimization problem. We derive necessary and sufficient conditions for the convergence of Monge maps without requiring optimality of the dual potential. This analysis helps explain why, in practice, numerical algorithms often require more iterations to update the transport map than the potential. |
| title | Stability of the Monge Map in Semi-Dual Optimal Transport |
| topic | Optimization and Control Machine Learning |
| url | https://arxiv.org/abs/2605.05569 |