Accelerating Convergence of Stein Variational Gradient Descent via Deep Unfolding

arXiv:2402.15125v1 Announce Type: new
Abstract: Stein variational gradient descent (SVGD) is a prominent particle-based variational inference method used for sampling a target distribution. SVGD has attracted interest for application in machine-learning techniques such as Bayesian inference. In this paper, we propose novel trainable algorithms that incorporate a deep-learning technique called deep unfolding,into SVGD. This approach facilitates the learning of the internal parameters of SVGD, thereby accelerating its convergence speed. To evaluate the proposed trainable SVGD algorithms, we conducted numerical simulations …

abstract algorithms application arxiv bayesian bayesian inference convergence cs.lg distribution gradient inference machine novel paper sampling stat.ml type via