A Particle Algorithm for Mean-Field Variational Inference
SIAM Journal on Optimization · 30.06.2026 · 36 (2) · 791-810
DOI: 10.1137/25m1767297 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Optimization, online erschienen am 30.04.2026. Verfasst von Qiang Du und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: National Science Foundation, U.S. Department of Energy.
Abstract (Originalsprache)
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.
Förderung
- National Science Foundation
- U.S. Department of Energy
Zitieren
APA
Du, Q., Wang, K., Zhang, E., & Zhong, C. (2026). A Particle Algorithm for Mean-Field Variational Inference. SIAM Journal on Optimization, 36(2), 791-810. https://doi.org/10.1137/25m1767297
Vancouver
Du Q, Wang K, Zhang E, Zhong C. A Particle Algorithm for Mean-Field Variational Inference. SIAM Journal on Optimization. 2026;36(2):791-810. doi:10.1137/25m1767297
BibTeX
@article{Du2026,
author = {Du, Qiang and Wang, Kaizheng and Zhang, Edith and Zhong, Chenyang},
title = {A Particle Algorithm for Mean-Field Variational Inference},
journal = {SIAM Journal on Optimization},
year = {2026},
volume = {36},
number = {2},
pages = {791--810},
doi = {10.1137/25m1767297}
}
EUVIMED