Understanding and accelerating particle-based variational inference

Chang Liu, Jingwei Zhuo, Pengyu Cheng, Ruiyi Zhang, Jun Zhu, Lawrence Carin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Particle-based variational inference methods (ParVIs) have gained attention in the Bayesian inference literature, for their capacity to yield flexible and accurate approximations. We explore ParVIs from the perspective of Wasscrstcin gradient flows, and make both theoretical and practical contributions. We unify various finite-particle approximations that existing ParVIs use, and recognize that the approximation is essentially a compulsory smoothing treatment, in either of two equivalent forms. This novel understanding reveals the assumptions and relations of existing ParVIs, and also inspires new ParVIs. We propose an acceleration framework and a principled bandwidth-selection method for general ParVIs; these are based on the developed theory and leverage the geometry of the Wasscrstcin space. Experimental results show the improved convergence by the acceleration framework and enhanced sample accuracy by the bandwidth-selection method.
Original languageEnglish (US)
Title of host publication36th International Conference on Machine Learning, ICML 2019
PublisherInternational Machine Learning Society (IMLS)rasmussen@ptd.net
Pages7187-7205
Number of pages19
ISBN (Print)9781510886988
StatePublished - Jan 1 2019
Externally publishedYes

Fingerprint Dive into the research topics of 'Understanding and accelerating particle-based variational inference'. Together they form a unique fingerprint.

Cite this