Skip to yearly menu bar Skip to main content


Understanding and Accelerating Particle-Based Variational Inference

Chang Liu · Jingwei Zhuo · Pengyu Cheng · RUIYI (ROY) ZHANG · Jun Zhu

Pacific Ballroom #232

Keywords: [ Monte Carlo Methods ] [ Bayesian Methods ] [ Approximate Inference ]


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 Wasserstein 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 Wasserstein space. Experimental results show the improved convergence by the acceleration framework and enhanced sample accuracy by the bandwidth-selection method.

Live content is unavailable. Log in and register to view live content