Convergence Rates for Distribution Matching with Sliced Optimal Transport
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908827629125632 |
|---|---|
| author | Thurin, Gauthier Boyer, Claire Nadjahi, Kimia |
| author_facet | Thurin, Gauthier Boyer, Claire Nadjahi, Kimia |
| contents | We study the slice-matching scheme, an efficient iterative method for distribution matching based on sliced optimal transport. We investigate convergence to the target distribution and derive quantitative non-asymptotic rates. To this end, we establish __ojasiewicz-type inequalities for the Sliced-Wasserstein objective. A key challenge is to control along the trajectory the constants in these inequalities. We show that this becomes tractable for Gaussian distributions. Specifically, eigenvalues are controlled when matching along random orthonormal bases at each iteration. We complement our theory with numerical experiments and illustrate the predicted dependence on dimension and step-size, as well as the stabilizing effect of orthonormal-basis sampling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_10691 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Convergence Rates for Distribution Matching with Sliced Optimal Transport Thurin, Gauthier Boyer, Claire Nadjahi, Kimia Machine Learning We study the slice-matching scheme, an efficient iterative method for distribution matching based on sliced optimal transport. We investigate convergence to the target distribution and derive quantitative non-asymptotic rates. To this end, we establish __ojasiewicz-type inequalities for the Sliced-Wasserstein objective. A key challenge is to control along the trajectory the constants in these inequalities. We show that this becomes tractable for Gaussian distributions. Specifically, eigenvalues are controlled when matching along random orthonormal bases at each iteration. We complement our theory with numerical experiments and illustrate the predicted dependence on dimension and step-size, as well as the stabilizing effect of orthonormal-basis sampling. |
| title | Convergence Rates for Distribution Matching with Sliced Optimal Transport |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.10691 |