Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.23429 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915365348442112 |
|---|---|
| author | Li, Yingyuan Wang, Aokun Wang, Zhongjian |
| author_facet | Li, Yingyuan Wang, Aokun Wang, Zhongjian |
| contents | In this work, we propose a novel machine learning approach to compute the optimal transport map between two continuous distributions from their unpaired samples, based on the DeepParticle methods. The proposed method leads to a min-min optimization during training and does not impose any restriction on the network structure. Theoretically we establish a weak convergence guarantee and a quantitative error bound between the learned map and the optimal transport map. Our numerical experiments validate the theoretical results and the effectiveness of the new approach, particularly on real-world tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_23429 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DPOT: A DeepParticle method for Computation of Optimal Transport with convergence guarantee Li, Yingyuan Wang, Aokun Wang, Zhongjian Machine Learning In this work, we propose a novel machine learning approach to compute the optimal transport map between two continuous distributions from their unpaired samples, based on the DeepParticle methods. The proposed method leads to a min-min optimization during training and does not impose any restriction on the network structure. Theoretically we establish a weak convergence guarantee and a quantitative error bound between the learned map and the optimal transport map. Our numerical experiments validate the theoretical results and the effectiveness of the new approach, particularly on real-world tasks. |
| title | DPOT: A DeepParticle method for Computation of Optimal Transport with convergence guarantee |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2506.23429 |