A Particle Algorithm for Mean-Field Variational Inference
Abstract
Abstract. Variational inference (VI) 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 nonasymptotic error bounds for our algorithm. To the best of our knowledge, this is the first end-to-end guarantee for particle-based MFVI.
Fields of Study & Subjects
Speech and Audio Processing
Publication details
- Journal / source
- SIAM Journal on Optimization
- Volume
- 36
- Issue
- 2
- Pages
- 791–810
- Publication date
- 30 April 2026
- Language
- EN