Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.13372 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912162492973056 |
|---|---|
| author | Shivakumar, Sachin Bondar, Georgiy A. Khan, Gabriel Halder, Abhishek |
| author_facet | Shivakumar, Sachin Bondar, Georgiy A. Khan, Gabriel Halder, Abhishek |
| contents | For a given ground cost, approximating the Monge optimal transport map that pushes forward a given probability measure onto another has become a staple in several modern machine learning algorithms. The fourth-order Ma-Trudinger-Wang (MTW) tensor associated with this ground cost function provides a notion of curvature in optimal transport. The non-negativity of this tensor plays a crucial role for establishing continuity for the Monge optimal transport map. It is, however, generally difficult to analytically verify this condition for any given ground cost. To expand the class of cost functions for which MTW non-negativity can be verified, we propose a provably correct computational approach which provides certificates of non-negativity for the MTW tensor using Sum-of-Squares (SOS) programming. We further show that our SOS technique can also be used to compute an inner approximation of the region where MTW non-negativity holds. We apply our proposed SOS programming method to several practical ground cost functions to approximate the regions of regularity of their corresponding optimal transport maps. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_13372 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Sum-of-Squares Programming for Ma-Trudinger-Wang Regularity of Optimal Transport Maps Shivakumar, Sachin Bondar, Georgiy A. Khan, Gabriel Halder, Abhishek Optimization and Control Artificial Intelligence Machine Learning Differential Geometry For a given ground cost, approximating the Monge optimal transport map that pushes forward a given probability measure onto another has become a staple in several modern machine learning algorithms. The fourth-order Ma-Trudinger-Wang (MTW) tensor associated with this ground cost function provides a notion of curvature in optimal transport. The non-negativity of this tensor plays a crucial role for establishing continuity for the Monge optimal transport map. It is, however, generally difficult to analytically verify this condition for any given ground cost. To expand the class of cost functions for which MTW non-negativity can be verified, we propose a provably correct computational approach which provides certificates of non-negativity for the MTW tensor using Sum-of-Squares (SOS) programming. We further show that our SOS technique can also be used to compute an inner approximation of the region where MTW non-negativity holds. We apply our proposed SOS programming method to several practical ground cost functions to approximate the regions of regularity of their corresponding optimal transport maps. |
| title | Sum-of-Squares Programming for Ma-Trudinger-Wang Regularity of Optimal Transport Maps |
| topic | Optimization and Control Artificial Intelligence Machine Learning Differential Geometry |
| url | https://arxiv.org/abs/2412.13372 |