mlsanityData to 14 Oct 2026

Learning Latent Energy-Based Models via Interacting Particle Langevin Dynamics

arXiv 2510.12311 ↗First posted 14 Oct 2025stat.ML cs.LG stat.COcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 61 of its 91 references that are in the map. First posted on arXiv 14 Oct 2025.

Builds on

61 of 91 references.

References · 61

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  3. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  5. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  6. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  7. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  8. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  9. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,043
  10. 2017PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modificationscited by 417
  11. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 405
  12. 2021How to Train Your Energy-Based Modelscited by 274
38 more
  1. 2019Residual Flows for Invertible Generative Modelingcited by 257
  2. 2017Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysiscited by 243
  3. 2023Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMCcited by 220
  4. 2015Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithmcited by 197
  5. 2019Diagnosing and Enhancing VAE Modelscited by 193
  6. 2019Learning Non-Convergent Non-Persistent Short-Run MCMC Toward Energy-Based Modelcited by 148
  7. 2019From Variational to Deterministic Autoencoderscited by 133
  8. 2020Improved Contrastive Divergence Training of Energy Based Modelscited by 130
  9. 2020Learning Energy-Based Models by Diffusion Recovery Likelihoodcited by 123
  10. 2017User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradientcited by 116
  11. 2016Deep Structured Energy Based Models for Anomaly Detectioncited by 114
  12. 2019On the Anatomy of MCMC-Based Maximum Likelihood Learning of Energy-Based Modelscited by 105
  13. 2020Learning Latent Space Energy-Based Prior Modelcited by 104
  14. 2020VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Modelscited by 104
  15. 2020Residual Energy-Based Models for Text Generationcited by 95
  16. 2019Flow Contrastive Estimation of Energy-Based Modelscited by 75
  17. 2020Generalized Energy Based Modelscited by 73
  18. 2020No MCMC for me: Amortized sampling for fast and stable training of energy-based modelscited by 64
  19. 2016Cooperative Training of Descriptor and Generator Networkscited by 60
  20. 2024Deep Generative Models through the Lens of the Manifold Hypothesis: A Survey and New Connectionscited by 47
  21. 2023Faster high-accuracy log-concave sampling via algorithmic warm startscited by 45
  22. 2022A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based Modelcited by 44
  23. 2020Learning Energy-Based Model with Variational Auto-Encoder as Amortized Samplercited by 43
  24. 2019Nonasymptotic estimates for Stochastic Gradient Langevin Dynamics under local conditions in nonconvex optimizationcited by 38
  25. 2018Divergence Triangle for Joint Training of Generator Model, Energy-based Model, and Inference Modelcited by 34
  26. 2018Autoregressive Quantile Networks for Generative Modelingcited by 31
  27. 2025Energy-Based Transformers are Scalable Learners and Thinkerscited by 31
  28. 2022Statistical exploration of the Manifold Hypothesiscited by 29
  29. 2020MCMC Should Mix: Learning Energy-Based Model with Neural Transport Latent Space MCMCcited by 26
  30. 2022Particle algorithms for maximum likelihood training of latent variable modelscited by 26
  31. 2023Learning Energy-Based Models by Cooperative Diffusion Recovery Likelihoodcited by 19
  32. 2022Adaptive Multi-stage Density Ratio Estimation for Learning Latent Space Energy-based Modelcited by 18
  33. 2023Interacting Particle Langevin Algorithm for Maximum Marginal Likelihood Estimationcited by 17
  34. 2023Efficient Training of Energy-Based Models Using Jarzynski Equalitycited by 15
  35. 2023Learning Energy-Based Prior Model with Diffusion-Amortized MCMCcited by 13
  36. 2024Error bounds for particle gradient descent, and extensions of the log-Sobolev and Talagrand inequalitiescited by 13
  37. 2023Momentum Particle Maximum Likelihoodcited by 12
  38. 2023Tuning-Free Maximum Likelihood Training of Latent Variable Models via Coin Bettingcited by 11

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Efficient Stochastic Optimisation via Sequential Monte Carlocited by 1
  2. 2026Momentum SVGD-EM for Accelerated Maximum Marginal Likelihood Estimationcited by 0
  3. 2026Learning Multimodal Energy-Based Model with Multimodal Variational Auto-Encoder via MCMC Revisioncited by 0
  4. 2026Particle-based Generalised Stochastic Optimisationcited by 0
  5. 2026Structure-Adaptive Tree Field Integratorscited by 0