De-randomizing MCMC dynamics with the diffusion Stein operator

Loading...
Thumbnail Image

Access rights

openAccess

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

2021

Major/Subject

Mcode

Degree programme

Language

en

Pages

11

Series

Advances in Neural Information Processing Systems 34 pre-proceedings (NeurIPS 2021), Advances in Neural Information Processing Systems

Abstract

Approximate Bayesian inference estimates descriptors of an intractable target distribution - in essence, an optimization problem within a family of distributions. For example, Langevin dynamics (LD) extracts asymptotically exact samples from a diffusion process because the time evolution of its marginal distributions constitutes a curve that minimizes the KL-divergence via steepest descent in the Wasserstein space. Parallel to LD, Stein variational gradient descent (SVGD) similarly minimizes the KL, albeit endowed with a novel Stein-Wasserstein distance, by deterministically transporting a set of particle samples, thus de-randomizes the stochastic diffusion process. We propose de-randomized kernel-based particle samplers to all diffusion-based samplers known as MCMC dynamics. Following previous work in interpreting MCMC dynamics, we equip the Stein-Wasserstein space with a fiber-Riemannian Poisson structure, with the capacity of characterizing a fiber-gradient Hamiltonian flow that simulates MCMC dynamics. Such dynamics discretizes into generalized SVGD (GSVGD), a Stein-type deterministic particle sampler, with particle updates coinciding with applying the diffusion Stein operator to a kernel function. We demonstrate empirically that GSVGD can de-randomize complex MCMC dynamics, which combine the advantages of auxiliary momentum variables and Riemannian structure, while maintaining the high sample quality from an interacting particle system.

Description

Keywords

Other note

Citation

Shen, Z, Heinonen, M & Kaski, S 2021, De-randomizing MCMC dynamics with the diffusion Stein operator . in Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021 . Advances in Neural Information Processing Systems, vol. 21, Neural Information Processing Systems Foundation, pp. 17507-17517, Conference on Neural Information Processing Systems, Virtual, Online, 06/12/2021 . < https://proceedings.neurips.cc/paper/2021/hash/9271905e840548b8cada6d60c0cfd93b-Abstract.html >