Research
Learning Latent Energy-Based Models via Interacting Particle Langevin Dynamics
arXiv:2510.12311v2 Announce Type: replace-cross Abstract: We develop interacting particle algorithms for learning latent variable models with energy-based priors. To do so, we leverage recent developm
arXiv:2510.12311v2 Announce Type: replace-cross Abstract: 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 empirically validate the effectiveness of our method on synthetic and image datasets and demonstrate that using a particle based approach offers significant improvement in computational efficiency.
Related
- Multi-Mode Quantum Annealing for Generative Representation Learning with Boltzmann Priors
- A Diffusive Classification Loss for Learning Energy-based Generative Models
- StrEBM: A Structured Latent Energy-Based Model for Blind Source Separation
- Conditional Score-Based Modeling of Effective Langevin Dynamics
Source: arXiv cs.LG | 2026-07-15