Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.11133 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914154986602496 |
|---|---|
| author | Greco, Giacomo Tamanini, Luca |
| author_facet | Greco, Giacomo Tamanini, Luca |
| contents | In this paper we determine quantitative stability bounds for the Hessian of entropic potentials, \ie, the dual solution to the entropic optimal transport problem. To the authors' knowledge this is the first work addressing this second-order quantitative stability estimate in general unbounded settings. Our proof strategy relies on semiconcavity properties of entropic potentials and on the representation of entropic transport plans as laws of forward and backward diffusion processes, known as Schrödinger bridges. Moreover, our approach allows to deduce a stochastic proof of quantitative stability estimates for entropic transport plans and for gradients of entropic potentials as well. Finally, as a direct consequence of these stability bounds, we deduce exponential convergence rates for gradient and Hessian of Sinkhorn iterates along Sinkhorn's algorithm, a problem that was still open in unbounded settings. Our rates have a polynomial dependence on the regularization parameter. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_11133 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hessian stability and convergence rates for entropic and Sinkhorn potentials via semiconcavity Greco, Giacomo Tamanini, Luca Probability Analysis of PDEs Optimization and Control Machine Learning 49Q22, 49L12, 39B62, 60J60, 68Q87, 68W40 In this paper we determine quantitative stability bounds for the Hessian of entropic potentials, \ie, the dual solution to the entropic optimal transport problem. To the authors' knowledge this is the first work addressing this second-order quantitative stability estimate in general unbounded settings. Our proof strategy relies on semiconcavity properties of entropic potentials and on the representation of entropic transport plans as laws of forward and backward diffusion processes, known as Schrödinger bridges. Moreover, our approach allows to deduce a stochastic proof of quantitative stability estimates for entropic transport plans and for gradients of entropic potentials as well. Finally, as a direct consequence of these stability bounds, we deduce exponential convergence rates for gradient and Hessian of Sinkhorn iterates along Sinkhorn's algorithm, a problem that was still open in unbounded settings. Our rates have a polynomial dependence on the regularization parameter. |
| title | Hessian stability and convergence rates for entropic and Sinkhorn potentials via semiconcavity |
| topic | Probability Analysis of PDEs Optimization and Control Machine Learning 49Q22, 49L12, 39B62, 60J60, 68Q87, 68W40 |
| url | https://arxiv.org/abs/2504.11133 |