Stochastic Particle-Optimization Sampling and the Non-Asymptotic Convergence Theory
Particle-optimization-based 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 yielding particle-optimization sampling (SPOS). Notably, for the first time, we develop {\em non-asymptotic convergence theory} for the SPOS framework (related to SVGD), characterizing algorithm convergence in terms of the 1-Wasserstein 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 an experiment on synthetic data. Extensive experimental results verify our theory and demonstrate the effectiveness of our proposed framework.
Code (0)
등록된 구현이 없습니다.
Tasks
POSSimilar Papers 제목 키워드 기반
Variance Reduction in Stochastic Particle-Optimization Sampling
Stochastic particle-optimization sampling (SPOS) is a recently-developed scalable Bayesian sampling framework that unifies stochastic gradient MCMC (SG-MCMC) and Stein variational gradient descent (SVGD) algorithms based…
POSTowards More Theoretically-Grounded Particle Optimization Sampling for Deep Learning
Many deep-learning based methods such as Bayesian deep learning (DL) and deep reinforcement learning (RL) have heavily relied on the ability of a model being able to efficiently explore via Bayesian sampling. Particle-op…
Deep LearningDeep Reinforcement LearningPOSReinforcement Learning (RL)Stochastic Multiple Target Sampling Gradient Descent
Sampling from an unnormalized target distribution is an essential problem with many applications in probabilistic inference. Stein Variational Gradient Descent (SVGD) has been shown to be a powerful method that iterative…
Multi-Task LearningImportance Sampling With Stochastic Particle Flow and Diffusion Optimization
Particle flow (PFL) is an effective method for overcoming particle degeneracy, the main limitation of particle filtering. In PFL, particles are migrated towards regions of high likelihood based on the solution of a parti…
Numerical IntegrationEfficient Online Learning in Interacting Particle Systems
We introduce a new method for online parameter estimation in stochastic interacting particle systems, based on continuous observation of a small number of particles from the system. Our method recursively updates the mod…