Bouncy Hybrid Sampler as a Unifying Device

TL;DR

This paper introduces the Bouncy Hybrid Sampler, a unifying rejection-free MCMC framework that encompasses existing methods and proposes a new quadratic variant, demonstrated on truncated Gaussian sampling.

Contribution

It unifies various rejection-free MCMC methods into a single framework and introduces a new quadratic Bouncy Hybrid Sampler for improved sampling.

Findings

Unified framework for rejection-free MCMC methods

Development of the Quadratic Bouncy Hybrid Sampler

Successful application to truncated Gaussian sampling

Abstract

This work introduces a class of rejection-free Markov chain Monte Carlo (MCMC) samplers, named the Bouncy Hybrid Sampler, which unifies several existing methods from the literature. Examples include the Bouncy Particle Sampler of Peters and de With (2012), Bouchard-Cote et al. (2015) and the Hamiltonian MCMC. Following the introduced general framework, we derive a new sampler called the Quadratic Bouncy Hybrid Sampler. We apply this novel sampler to the problem of sampling from a truncated Gaussian distribution.