Automatic Zig-Zag sampling in practice

TL;DR

This paper introduces a practical implementation of the Zig-Zag sampler, a PDMP-based Monte Carlo method, addressing previous challenges and demonstrating its efficiency and applicability in real-world Bayesian sampling tasks.

Contribution

The paper presents a new, implementable algorithm for the Zig-Zag sampler that requires only the target density function and proves its practical efficiency and super-efficiency.

Findings

The algorithm is competitive with gradient-based samplers.

It requires only the target density, simplifying implementation.

Super-efficiency is achievable in practice.

Abstract

Novel Monte Carlo methods to generate samples from a target distribution, such as a posterior from a Bayesian analysis, have rapidly expanded in the past decade. Algorithms based on Piecewise Deterministic Markov Processes (PDMPs), non-reversible continuous-time processes, are developing into their own research branch, thanks their important properties (e.g., correct invariant distribution, ergodicity, and super-efficiency). Nevertheless, practice has not caught up with the theory in this field, and the use of PDMPs to solve applied problems is not widespread. This might be due, firstly, to several implementational challenges that PDMP-based samplers present with and, secondly, to the lack of papers that showcase the methods and implementations in applied settings. Here, we address both these issues using one of the most promising PDMPs, the Zig-Zag sampler, as an archetypal example. After an explanation of the key elements of the Zig-Zag sampler, its implementation challenges are exposed and addressed. Specifically, the formulation of an algorithm that draws samples from a target distribution of interest is provided. Notably, the only requirement of the algorithm is a closed-form function to evaluate the target density of interest, and, unlike previous implementations, no further information on the target is needed. The performance of the algorithm is evaluated against another gradient-based sampler, and it is proven to be competitive, in simulation and real-data settings. Lastly, we demonstrate that the super-efficiency property, i.e. the ability to draw one independent sample at a lesser cost than evaluating the likelihood of all the data, can be obtained in practice.