Learning Latent Energy-Based Models via Interacting Particle Langevin Dynamics
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_ | 1866908591919726592 |
|---|---|
| author | Marks, Joanna Wang, Tim Y. J. Akyildiz, O. Deniz |
| author_facet | Marks, Joanna Wang, Tim Y. J. Akyildiz, O. Deniz |
| contents | We develop interacting particle algorithms for learning latent variable models with energy-based priors. To do so, we leverage recent developments in particle-based methods for solving maximum marginal likelihood estimation (MMLE) problems. Specifically, we provide a continuous-time framework for learning latent energy-based models, by defining stochastic differential equations (SDEs) that provably solve the MMLE problem. We obtain a practical algorithm as a discretisation of these SDEs and provide theoretical guarantees for the convergence of the proposed algorithm. Finally, we demonstrate the empirical effectiveness of our method on synthetic and image datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_12311 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning Latent Energy-Based Models via Interacting Particle Langevin Dynamics Marks, Joanna Wang, Tim Y. J. Akyildiz, O. Deniz Machine Learning Computation We develop interacting particle algorithms for learning latent variable models with energy-based priors. To do so, we leverage recent developments in particle-based methods for solving maximum marginal likelihood estimation (MMLE) problems. Specifically, we provide a continuous-time framework for learning latent energy-based models, by defining stochastic differential equations (SDEs) that provably solve the MMLE problem. We obtain a practical algorithm as a discretisation of these SDEs and provide theoretical guarantees for the convergence of the proposed algorithm. Finally, we demonstrate the empirical effectiveness of our method on synthetic and image datasets. |
| title | Learning Latent Energy-Based Models via Interacting Particle Langevin Dynamics |
| topic | Machine Learning Computation |
| url | https://arxiv.org/abs/2510.12311 |