A Particle Algorithm for Mean-Field Variational Inference
Not on the map. Why?
Abstract (arXiv)
Variational inference is a fast and scalable alternative to Markov chain Monte Carlo and has been widely applied to posterior inference tasks in statistics and machine learning. A traditional approach for implementing mean-field variational inference (MFVI) is coordinate ascent variational inference (CAVI), which relies crucially on parametric assumptions on complete conditionals. We introduce a novel particle-based algorithm for MFVI, named PArticle VI (PAVI), for nonparametric mean-field approximation. We obtain non-asymptotic error bounds for our algorithm. To our knowledge, this is the first end-to-end guarantee for particle-based MFVI.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 29 of its 47 references that are in the map. First posted on arXiv 29 Dec 2024.
Builds on
29 of 47 references.
References · 29
- 2016Variational Inference: A Review for Statisticianscited by 1,466
- 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 498
- 2018On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transportcited by 422
- 2014Theoretical guarantees for approximate sampling from smooth and log-concave densitiescited by 206
- 2015Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithmcited by 195
- 2018Analysis of Langevin Monte Carlo via convex optimizationcited by 126
- 2017Convergence of Langevin MCMC in KL-divergencecited by 86
- 2022Variational inference via Wasserstein gradient flowscited by 84
- 2022Towards a Theory of Non-Log-Concave Sampling: First-Order Stationarity Guarantees for Langevin Monte Carlocited by 63
- 2020A Non-Asymptotic Analysis for Stein Variational Gradient Descentcited by 61
- 2017Convergence Rates of Variational Posterior Distributionscited by 45
- 2019Accelerating Langevin Sampling with Birth-deathcited by 45
17 more
- 2019Accelerated Information Gradient flowcited by 38
- 2023Forward-backward Gaussian variational inference via JKO in the Bures-Wasserstein Spacecited by 36
- 2022Birth-death dynamics for sampling: Global convergence, approximations and their asymptoticscited by 30
- 2023Learning Gaussian Mixtures Using the Wasserstein-Fisher-Rao Gradient Flowcited by 25
- 2020Information Newton's flow: second-order optimization method in probability spacecited by 22
- 2023Algorithms for mean-field variational inference via polyhedral optimization in the Wasserstein spacecited by 20
- 2022Mean-field Variational Inference via Wasserstein Gradient Flowcited by 19
- 2014Variational Particle Approximationscited by 13
- 2023Towards Understanding the Dynamics of Gaussian-Stein Variational Gradient Descentcited by 13
- 2023Independent projections of diffusions: Gradient flows for variational inference and optimal mean field approximationscited by 12
- 2024Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussianscited by 11
- 2021Variational Inference in high-dimensional linear regressioncited by 10
- 2023Particle-based Variational Inference with Generalized Wasserstein Gradient Flowcited by 10
- 2023Accelerating optimization over the space of probability measurescited by 9
- 2023Bridging the Gap Between Variational Inference and Wasserstein Gradient Flowscited by 8
- 2024Sampling from the Mean-Field Stationary Distributioncited by 7
- 2024Wasserstein Proximal Coordinate Gradient Algorithmscited by 7
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.