Stochastic ParticleOptimization Sampling and the NonAsymptotic Convergence Theory
[edit]
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, PMLR 108:18771887, 2020.
Abstract
Particleoptimizationbased sampling (POS) is a recently developed effective sampling technique that interactively updates a set of particles. A representative algorithm is the Stein variational gradient descent (SVGD). We prove, under certain conditions, SVGD experiences a theoretical pitfall, {\it i.e.}, particles tend to collapse. As a remedy, we generalize POS to a stochastic setting by injecting random noise into particle updates, thus termed stochastic particleoptimization sampling (SPOS). Notably, for the first time, we develop nonasymptotic convergence theory for the SPOS framework (related to SVGD), characterizing algorithm convergence in terms of the 1Wasserstein distance w.r.t. the numbers of particles and iterations. Somewhat surprisingly, with the same number of updates (not too large) for each particle, our theory suggests adopting more particles does not necessarily lead to a better approximation of a target distribution, due to limited computational budget and numerical errors. This phenomenon is also observed in SVGD and verified via a synthetic experiment. Extensive experimental results verify our theory and demonstrate the effectiveness of our proposed framework.
Related Material


