Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2508.02770 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918121989734400 |
|---|---|
| author | Sokolov, Kirill Korotin, Alexander |
| author_facet | Sokolov, Kirill Korotin, Alexander |
| contents | We consider the discrete-time Schrödinger bridge problem on a finite state space. Although it has been known that the Iterative Markovian Fitting (IMF) algorithm converges in Kullback-Leibler divergence to the ground truth solution, the speed of that convergence remained unquantified. In this work, we establish for the first time that IMF exhibits exponential convergence with an explicit contraction factor. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_02770 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exponential convergence rate for Iterative Markovian Fitting Sokolov, Kirill Korotin, Alexander Information Theory Machine Learning We consider the discrete-time Schrödinger bridge problem on a finite state space. Although it has been known that the Iterative Markovian Fitting (IMF) algorithm converges in Kullback-Leibler divergence to the ground truth solution, the speed of that convergence remained unquantified. In this work, we establish for the first time that IMF exhibits exponential convergence with an explicit contraction factor. |
| title | Exponential convergence rate for Iterative Markovian Fitting |
| topic | Information Theory Machine Learning |
| url | https://arxiv.org/abs/2508.02770 |