Binary Bouncy Particle Sampler
Ari Pakman

TL;DR
This paper introduces a generalized binary Bouncy Particle Sampler that efficiently samples from binary distributions, outperforming binary Hamiltonian Monte Carlo in certain scenarios, especially for distributions that are easy to mix.
Contribution
The paper extends the Bouncy Particle Sampler to binary distributions via a piecewise differentiable augmentation, enabling efficient sampling in binary Markov Random Fields.
Findings
Binary BPS outperforms binary HMC on easy-to-mix distributions.
The algorithm effectively handles piecewise differentiable binary distributions.
Application demonstrated on binary Markov Random Fields.
Abstract
The Bouncy Particle Sampler is a novel rejection-free non-reversible sampler for differentiable probability distributions over continuous variables. We generalize the algorithm to piecewise differentiable distributions and apply it to generic binary distributions using a piecewise differentiable augmentation. We illustrate the new algorithm in a binary Markov Random Field example, and compare it to binary Hamiltonian Monte Carlo. Our results suggest that binary BPS samplers are better for easy to mix distributions.
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
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsBayesian Methods and Mixture Models · Markov Chains and Monte Carlo Methods · Statistical Methods and Bayesian Inference
