The Boomerang Sampler
Joris Bierkens, Sebastiano Grazzi, Kengo Kamatani, Gareth Roberts

TL;DR
The Boomerang Sampler is a new continuous-time non-reversible MCMC method that constructs elliptical trajectories for efficient sampling, outperforming existing algorithms and scaling well with large data, especially with subsampling techniques.
Contribution
It introduces the Boomerang Sampler, a novel non-reversible MCMC algorithm with a new elliptical trajectory approach, and demonstrates its efficiency and scalability, including subsampling variants.
Findings
Outperforms existing piecewise deterministic Markov processes.
Can be combined with exact data subsampling techniques.
Exhibits remarkable scaling properties in large data settings.
Abstract
This paper introduces the Boomerang Sampler as a novel class of continuous-time non-reversible Markov chain Monte Carlo algorithms. The methodology begins by representing the target density as a density, , with respect to a prescribed (usually) Gaussian measure and constructs a continuous trajectory consisting of a piecewise elliptical path. The method moves from one elliptical orbit to another according to a rate function which can be written in terms of . We demonstrate that the method is easy to implement and demonstrate empirically that it can out-perform existing benchmark piecewise deterministic Markov processes such as the bouncy particle sampler and the Zig-Zag. In the Bayesian statistics context, these competitor algorithms are of substantial interest in the large data context due to the fact that they can adopt data subsampling techniques which are exact (ie induce…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Taxonomy
TopicsMarkov Chains and Monte Carlo Methods · Bayesian Methods and Mixture Models · Statistical Methods and Bayesian Inference
MethodsDiffusion
