mlsanityData to 7 Oct 2026

Particle Mean Field Variational Bayes

arXiv 2303.13930 ↗First posted 24 Mar 2023stat.CO cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

The Mean Field Variational Bayes (MFVB) method is one of the most computationally efficient techniques for Bayesian inference. However, its use has been restricted to models with conjugate priors or those that require analytical calculations. This paper proposes a novel particle-based MFVB approach that greatly expands the applicability of the MFVB method. We establish the theoretical basis of the new method by leveraging the connection between Wasserstein gradient flows and Langevin diffusion dynamics, and demonstrate the effectiveness of this approach using Bayesian logistic regression, stochastic volatility, and deep neural networks.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 13 of its 40 references that are in the map. First posted on arXiv 24 Mar 2023.

Builds on

13 of 40 references.

References · 13

  1. 2016Variational Inference: A Review for Statisticianscited by 1,466
  2. 2014Stochastic Gradient Hamiltonian Monte Carlocited by 341
  3. 2014Theoretical guarantees for approximate sampling from smooth and log-concave densitiescited by 206
  4. 2015Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networkscited by 121
  5. 2017Convergence of Langevin MCMC in KL-divergencecited by 86
  6. 2022Variational inference via Wasserstein gradient flowscited by 84
  7. 2017Concentration of tempered posteriors and of their variational approximationscited by 66
  8. 2017Convergence Rates of Variational Posterior Distributionscited by 45
  9. 2017Theoretical and Computational Guarantees of Mean Field Variational Inference for Community Detectioncited by 19
  10. 2022Mean-field Variational Inference via Wasserstein Gradient Flowcited by 19
  11. 2014Speeding Up MCMC by Efficient Data Subsamplingcited by 18
  12. 2013Inferring Parameters and Structure of Latent Variable Models by Variational Bayescited by 11
1 more
  1. 2018Use of model reparametrization to improve variational Bayescited by 1

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 0; 2025: 2.

4 papers.

  1. 2023Algorithms for mean-field variational inference via polyhedral optimization in the Wasserstein spacecited by 20
  2. 2023Independent projections of diffusions: Gradient flows for variational inference and optimal mean field approximationscited by 12
  3. 2025Rotated Mean-Field Variational Inference and Iterative Gaussianizationcited by 1
  4. 2025On weight and variance uncertainty in neural networks for regression taskscited by 0