Particle-based Online Bayesian Sampling
Abstract: Online learning has gained increasing interest due to its capability of tracking real-world streaming data. Although it has been widely studied in the setting of frequentist statistics, few works have considered online learning with the Bayesian sampling problem. In this paper, we study an Online Particle-based Variational Inference (OPVI) algorithm that updates a set of particles to gradually approximate the Bayesian posterior. To reduce the gradient error caused by the use of stochastic approximation, we include a sublinear increasing batch-size method to reduce the variance. To track the performance of the OPVI algorithm concerning a sequence of dynamically changing target posterior, we provide the first theoretical analysis for the dynamic regret from the perspective of Wasserstein gradient flow. Experimental results on the Bayesian Neural Network show that the proposed algorithm achieves up to 20\% improvement than naively applying existing Bayesian sampling methods in the online setting.
Submission Length: Regular submission (no more than 12 pages of main content)
Assigned Action Editor: ~Konstantin_Mishchenko1
Submission Number: 2266
Loading