Faster Computation of Entropic Optimal Transport via Stable Low Frequency Modes
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_ | 1866916797349888000 |
|---|---|
| author | Chhaibi, Reda Gratton, Serge Vaiter, Samuel |
| author_facet | Chhaibi, Reda Gratton, Serge Vaiter, Samuel |
| contents | In this paper, we propose an accelerated version for the Sinkhorn algorithm, which is the reference method for computing the solution to Entropic Optimal Transport.
Its main draw-back is the exponential slow-down of convergence as the regularization weakens $\varepsilon \rightarrow 0$.
Thanks to spectral insights on the behavior of the Hessian, we propose to mitigate the problem via an original spectral warm-start strategy. This leads to faster convergence compared to the reference method, as also demonstrated in our numerical experiments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_14780 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Faster Computation of Entropic Optimal Transport via Stable Low Frequency Modes Chhaibi, Reda Gratton, Serge Vaiter, Samuel Numerical Analysis Optimization and Control Probability Computation Machine Learning In this paper, we propose an accelerated version for the Sinkhorn algorithm, which is the reference method for computing the solution to Entropic Optimal Transport. Its main draw-back is the exponential slow-down of convergence as the regularization weakens $\varepsilon \rightarrow 0$. Thanks to spectral insights on the behavior of the Hessian, we propose to mitigate the problem via an original spectral warm-start strategy. This leads to faster convergence compared to the reference method, as also demonstrated in our numerical experiments. |
| title | Faster Computation of Entropic Optimal Transport via Stable Low Frequency Modes |
| topic | Numerical Analysis Optimization and Control Probability Computation Machine Learning |
| url | https://arxiv.org/abs/2506.14780 |