GAD-PVI: A General Accelerated Dynamic-Weight Particle-Based Variational Inference Framework.

ABSTRACT: Particle-based Variational Inference (ParVI) methods have been widely adopted in deep Bayesian inference tasks such as Bayesian neural networks or Gaussian Processes, owing to their efficiency in generating high-quality samples given the score of the target distribution. Typically, ParVI methods evolve a weighted-particle system by approximating the first-order Wasserstein gradient flow to reduce the dissimilarity between the particle system's empirical distribution and the target distribution. Recent advancements in ParVI have explored sophisticated gradient flows to obtain refined particle systems with either accelerated position updates or dynamic weight adjustments. In this paper, we introduce the semi-Hamiltonian gradient flow on a novel Information-Fisher-Rao space, known as the SHIF

SUBMITTER: Wang F 

PROVIDER: S-EPMC11354113 | biostudies-literature | 2024 Aug

REPOSITORIES: biostudies-literature