A Particle Algorithm for Mean-Field Variational Inference
Statistics Theory
2026-01-01 v4 Machine Learning
Optimization and Control
Machine Learning
Statistics Theory
Abstract
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.
Cite
@article{arxiv.2412.20385,
title = {A Particle Algorithm for Mean-Field Variational Inference},
author = {Qiang Du and Kaizheng Wang and Edith Zhang and Chenyang Zhong},
journal= {arXiv preprint arXiv:2412.20385},
year = {2026}
}
Comments
22 pages