mlsanityData to 7 Oct 2026

Particle algorithms for maximum likelihood training of latent variable models

arXiv 2204.12965 ↗First posted 27 Apr 2022stat.CO cs.LG math.OCcited by 26

Not on the map. Why?

Abstract (arXiv)

(Neal and Hinton, 1998) recast maximum likelihood estimation of any given latent variable model as the minimization of a free energy functional F, and the EM algorithm as coordinate descent applied to F. Here, we explore alternative ways to optimize the functional. In particular, we identify various gradient flows associated with F and show that their limits coincide with F's stationary points. By discretizing the flows, we obtain practical particle-based algorithms for maximum likelihood estimation in broad classes of latent variable models. The novel algorithms scale to high-dimensional settings and perform well in numerical experiments.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 43 of its 114 references that are in the map. First posted on arXiv 27 Apr 2022.

Builds on

43 of 114 references.

References · 43

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  6. 2021Convex optimizationcited by 2,479
  7. 2016An overview of gradient descent optimization algorithmscited by 1,021
  8. 2019An Introduction to Variational Autoencoderscited by 997
  9. 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 498
  10. 2014New insights and perspectives on the natural gradient methodcited by 435
  11. 2017VAE with a VampPriorcited by 247
  12. 2014Theoretical guarantees for approximate sampling from smooth and log-concave densitiescited by 206
31 more
  1. 2015Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithmcited by 195
  2. 2019Diagnosing and Enhancing VAE Modelscited by 192
  3. 2016High-dimensional Bayesian inference via the Unadjusted Langevin Algorithmcited by 144
  4. 2017Underdamped Langevin MCMC: A non-asymptotic analysiscited by 131
  5. 2018Analysis of Langevin Monte Carlo via convex optimizationcited by 126
  6. 2015Practical Bayesian model evaluation using leave-one-out cross-validation and WAICcited by 110
  7. 2020Learning Latent Space Energy-Based Prior Modelcited by 104
  8. 2021Oops I Took A Gradient: Scalable Sampling for Discrete Distributionscited by 92
  9. 2017Convergence of Langevin MCMC in KL-divergencecited by 86
  10. 2016Efficient Bayesian computation by proximal Markov chain Monte Carlo: when Langevin meets Moreaucited by 83
  11. 2019On the geometry of Stein variational gradient descentcited by 82
  12. 2020A Contrastive Learning Approach for Training Variational Autoencoder Priorscited by 65
  13. 2018Mirrored Langevin Dynamicscited by 61
  14. 2018Resampled Priors for Variational Autoencoderscited by 56
  15. 2019Stochastic gradient Markov chain Monte Carlocited by 56
  16. 2020Wasserstein Control of Mirror Langevin Monte Carlocited by 55
  17. 2020Efficient constrained sampling via the mirror-Langevin algorithmcited by 55
  18. 2019Learning Hierarchical Priors in VAEscited by 53
  19. 2013Proximal Markov chain Monte Carlo algorithmscited by 46
  20. 2019Accelerating Langevin Sampling with Birth-deathcited by 45
  21. 2019Accelerated Information Gradient flowcited by 38
  22. 2020Exponential ergodicity of mirror-Langevin diffusionscited by 37
  23. 2018Distribution Matching in Variational Inferencecited by 35
  24. 2020Primal Dual Interpretation of the Proximal Stochastic Gradient Langevin Algorithmcited by 34
  25. 2017Bayesian GANcited by 31
  26. 2020Stacking for Non-mixing Bayesian Computations: The Curse and Blessing of Multimodal Posteriorscited by 29
  27. 2019Is There an Analog of Nesterov Acceleration for MCMC?cited by 19
  28. 2019Accelerated Flow for Probability Distributionscited by 15
  29. 2021DPVI: A Dynamic-Weight Particle-Based Variational Inference Frameworkcited by 7
  30. 2022Optimal design of the Barker proposal and other locally-balanced Metropolis-Hastings algorithmscited by 7
  31. 2020Stochastic Approximate Gradient Descent via the Langevin Algorithmcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 11; 2025: 7; 2026: 6.

26 papers.

Sort:

By area:

  1. 2024Implicit Diffusion: Efficient Optimization through Stochastic Samplingcited by 22
  2. 2023Interacting Particle Langevin Algorithm for Maximum Marginal Likelihood Estimationcited by 17
  3. 2024Error bounds for particle gradient descent, and extensions of the log-Sobolev and Talagrand inequalitiescited by 13
  4. 2023Momentum Particle Maximum Likelihoodcited by 12
  5. 2024Proximal Interacting Particle Langevin Algorithmscited by 8
  6. 2024Particle Semi-Implicit Variational Inferencecited by 7
  7. 2024Kinetic Interacting Particle Langevin Monte Carlocited by 7
  8. 2024Stochastic Approximation with Biased MCMC for Expectation Maximizationcited by 5
  9. 2025Sequential Monte Carlo approximations of Wasserstein--Fisher--Rao gradient flowscited by 5
  10. 2025Training Latent Diffusion Models with Interacting Particle Algorithmscited by 4
  11. 2024Taming the Interacting Particle Langevin Algorithm: The Superlinear casecited by 3
  12. 2024Divide-and-Conquer Predictive Coding: a structured Bayesian inference algorithmcited by 3
14 more
  1. 2025Learning Latent Variable Models via Jarzynski-adjusted Langevin Algorithmcited by 3
  2. 2025Learning Latent Energy-Based Models via Interacting Particle Langevin Dynamicscited by 3
  3. 2024Scalable Vertical Federated Learning via Data Augmentation and Amortized Inferencecited by 2
  4. 2024How to beat a Bayesian adversarycited by 1
  5. 2024Fast convergence of the Expectation Maximization algorithm under a logarithmic Sobolev inequalitycited by 1
  6. 2026Efficient Stochastic Optimisation via Sequential Monte Carlocited by 1
  7. 2026Consistency Regularised Gradient Flows for Inverse Problemscited by 1
  8. 2025Sparse Techniques for Regression in Deep Gaussian Processescited by 0
  9. 2025A Gradient Flow Approach to Solving Inverse Problems with Latent Diffusion Modelscited by 0
  10. 2025Particle Dynamics for Latent-Variable Energy-Based Modelscited by 0
  11. 2026Momentum SVGD-EM for Accelerated Maximum Marginal Likelihood Estimationcited by 0
  12. 2026Properties and limitations of geometric tempering for gradient flow dynamicscited by 0
  13. 2026Tempered Guided Diffusioncited by 0
  14. 2026Particle-based Generalised Stochastic Optimisationcited by 0