Learning latent variable models via Jarzynski-adjusted Langevin algorithm
Author(s)
Cuin, Jamie
Carbone, Davide
Akyildiz, O Deniz
Type
Conference Paper
Abstract
We utilise a sampler originating from nonequilibrium statistical mechanics, termed here Jarzynski-adjusted Langevin algorithm (JALA), to build statistical estimation
methods in latent variable models. We achieve this by leveraging Jarzynski’s equality and developing algorithms based on a weighted version of the unadjusted Langevin algorithm (ULA) with recursively updated weights. Adapting this for latent variable models, we develop a sequential Monte Carlo (SMC) method that provides the maximum marginal likelihood estimate of the parameters, termed JALA-EM. Under suitable regularity assumptions on the marginal likelihood, we provide a nonasymptotic analysis of the JALA-EM scheme implemented with
stochastic gradient descent and show that it provably converges to the maximum marginal likelihood estimate. We demonstrate the performance of JALA-EM on a
variety of latent variable models and show that it performs comparably to existing methods in terms of accuracy and computational efficiency. Importantly, the ability to recursively estimate marginal likelihoods—an uncommon feature among scalable methods—makes our approach particularly suited for model selection, which we validate through dedicated experiments.
methods in latent variable models. We achieve this by leveraging Jarzynski’s equality and developing algorithms based on a weighted version of the unadjusted Langevin algorithm (ULA) with recursively updated weights. Adapting this for latent variable models, we develop a sequential Monte Carlo (SMC) method that provides the maximum marginal likelihood estimate of the parameters, termed JALA-EM. Under suitable regularity assumptions on the marginal likelihood, we provide a nonasymptotic analysis of the JALA-EM scheme implemented with
stochastic gradient descent and show that it provably converges to the maximum marginal likelihood estimate. We demonstrate the performance of JALA-EM on a
variety of latent variable models and show that it performs comparably to existing methods in terms of accuracy and computational efficiency. Importantly, the ability to recursively estimate marginal likelihoods—an uncommon feature among scalable methods—makes our approach particularly suited for model selection, which we validate through dedicated experiments.
Date Issued
2025-12-02
Date Acceptance
2025-09-18
Citation
Advances in Neural Information Processing Systems, 2025, 38, pp.106837-106876
ISSN
1049-5258
Publisher
Curran Associates, Inc.
Start Page
106837
End Page
106876
Journal / Book Title
Advances in Neural Information Processing Systems
Volume
38
Copyright Statement
© 2025 Neural Information Processing Systems Foundation, Inc. (NeurIPS)
Source
NeurIPS 2025
Publication Status
Published online
Start Date
2025-12-02
Finish Date
2025-12-07
Coverage Spatial
San Diego, CA, USA