Machine-Learned Sampling of Conditioned Path Measures
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_ | 1866912409608781824 |
|---|---|
| author | Jiang, Qijia Cohn-Gordon, Reuben |
| author_facet | Jiang, Qijia Cohn-Gordon, Reuben |
| contents | We propose algorithms for sampling from posterior path measures $P(C([0, T], \mathbb{R}^d))$ under a general prior process. This leverages ideas from (1) controlled equilibrium dynamics, which gradually transport between two path measures, and (2) optimization in $\infty$-dimensional probability space endowed with a Wasserstein metric, which can be used to evolve a density curve under the specified likelihood. The resulting algorithms are theoretically grounded and can be integrated seamlessly with neural networks for learning the target trajectory ensembles, without access to data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_01904 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Machine-Learned Sampling of Conditioned Path Measures Jiang, Qijia Cohn-Gordon, Reuben Machine Learning Computation We propose algorithms for sampling from posterior path measures $P(C([0, T], \mathbb{R}^d))$ under a general prior process. This leverages ideas from (1) controlled equilibrium dynamics, which gradually transport between two path measures, and (2) optimization in $\infty$-dimensional probability space endowed with a Wasserstein metric, which can be used to evolve a density curve under the specified likelihood. The resulting algorithms are theoretically grounded and can be integrated seamlessly with neural networks for learning the target trajectory ensembles, without access to data. |
| title | Machine-Learned Sampling of Conditioned Path Measures |
| topic | Machine Learning Computation |
| url | https://arxiv.org/abs/2506.01904 |