On the contraction properties of Sinkhorn semigroups
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912852933083136 |
|---|---|
| author | Akyildiz, O. Deniz del Moral, Pierre Miguez, Joaquin |
| author_facet | Akyildiz, O. Deniz del Moral, Pierre Miguez, Joaquin |
| contents | We develop a novel stability theory for Sinkhorn semigroups based on Lyapunov techniques and quantitative contraction coefficients, and establish exponential convergence of Sinkhorn iterations on weighted Banach spaces. This operator-theoretic framework yields explicit exponential decay rates of Sinkhorn iterates toward Schrödinger bridges with respect to a broad class of $ϕ$-divergences and Kantorovich-type distances, including relative entropy, squared Hellinger integrals, $α$-divergences, weighted total variation norms, and Wasserstein distances. To the best of our knowledge, these results provide the first systematic contraction inequalities of this kind for entropic transport and the Sinkhorn algorithm. We further introduce Lyapunov contraction principles under minimal regularity assumptions, leading to quantitative exponential stability estimates for a large family of Sinkhorn semigroups. The framework applies to models with polynomially growing potentials and heavy-tailed marginals on general normed spaces, as well as to more structured boundary state-space models, including semicircle transitions and Beta, Weibull, and exponential marginals, together with semi-compact settings. Finally, our approach extends naturally to statistical finite mixtures of such models, including kernel-based density estimators arising in modern generative modeling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_09887 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | On the contraction properties of Sinkhorn semigroups Akyildiz, O. Deniz del Moral, Pierre Miguez, Joaquin Probability Computation Machine Learning 37M25, 49Q22, 47H09, 60J20, secondary: 60J05, 94A17 We develop a novel stability theory for Sinkhorn semigroups based on Lyapunov techniques and quantitative contraction coefficients, and establish exponential convergence of Sinkhorn iterations on weighted Banach spaces. This operator-theoretic framework yields explicit exponential decay rates of Sinkhorn iterates toward Schrödinger bridges with respect to a broad class of $ϕ$-divergences and Kantorovich-type distances, including relative entropy, squared Hellinger integrals, $α$-divergences, weighted total variation norms, and Wasserstein distances. To the best of our knowledge, these results provide the first systematic contraction inequalities of this kind for entropic transport and the Sinkhorn algorithm. We further introduce Lyapunov contraction principles under minimal regularity assumptions, leading to quantitative exponential stability estimates for a large family of Sinkhorn semigroups. The framework applies to models with polynomially growing potentials and heavy-tailed marginals on general normed spaces, as well as to more structured boundary state-space models, including semicircle transitions and Beta, Weibull, and exponential marginals, together with semi-compact settings. Finally, our approach extends naturally to statistical finite mixtures of such models, including kernel-based density estimators arising in modern generative modeling. |
| title | On the contraction properties of Sinkhorn semigroups |
| topic | Probability Computation Machine Learning 37M25, 49Q22, 47H09, 60J20, secondary: 60J05, 94A17 |
| url | https://arxiv.org/abs/2503.09887 |