Piecewise-Deterministic Markov Chain Monte Carlo

Abstract

A novel class of non-reversible Markov chain Monte Carlo schemes relying on continuous-time piecewise-deterministic Markov Processes has recently emerged. In these algorithms, the state of the Markov process evolves according to a deterministic dynamics which is modified using a Markov transition kernel at random event times. These methods enjoy remarkable features including the ability to update only a subset of the state components while other components implicitly keep evolving and the ability to use an unbiased estimate of the gradient of the log-target while preserving the target as invariant distribution. However, they also suffer from important limitations. The deterministic dynamics used so far do not exploit the structure of the target. Moreover, exact simulation of the event times is feasible for an important yet restricted class of problems and, even when it is, it is application specific. This limits the applicability of these techniques and prevents the development of a generic software implementation of them. We introduce novel MCMC methods addressing these shortcomings. In particular, we introduce novel continuous-time algorithms relying on exact Hamiltonian flows and novel non-reversible discrete-time algorithms which can exploit complex dynamics such as approximate Hamiltonian dynamics arising from symplectic integrators while preserving the attractive features of continuous-time algorithms. We demonstrate the performance of these schemes on a variety of applications.

42 pages, 4 figures

References in corpus (1)

• Accelerating MCMC via Parallel Predictive Prefetching

Cited by in corpus (26)

• Ergodicity of the zigzag process
• Unbiased Markov chain Monte Carlo with couplings
• On explicit $L^2$-convergence rate estimate for piecewise deterministic Markov processes in MCMC algorithms
• Regeneration-enriched Markov processes with application to Monte Carlo
• Accelerated Sampling on Discrete Spaces with Non-Reversible Markov Processes
• Importance sampling correction versus standard averages of reversible MCMCs in terms of the asymptotic variance
• A general perspective on the Metropolis-Hastings kernel
• Geometric Methods for Sampling, Optimisation, Inference and Adaptive Agents
• Cores for Piecewise-Deterministic Markov Processes used in Markov Chain Monte Carlo
• Complexity of zigzag sampling algorithm for strongly log-concave distributions
• Binary Bouncy Particle Sampler
• The Coordinate Sampler: A Non-Reversible Gibbs-like MCMC Sampler
• Delayed rejection Hamiltonian Monte Carlo for sampling multiscale distributions
• Constructing sampling schemes via coupling: Markov semigroups and optimal transport
• Parallelising MCMC via Random Forests
• Scalable Metropolis-Hastings for Exact Bayesian Inference with Large Datasets
• Velocity Jumps for Molecular Dynamics
• Analysis of high-dimensional Continuous Time Markov Chains using the Local Bouncy Particle Sampler
• Efficient posterior sampling for high-dimensional imbalanced logistic regression
• Zigzag path connects two Monte Carlo samplers: Hamiltonian counterpart to a piecewise deterministic Markov process
• Piecewise deterministic sampling with splitting schemes
• A note on the jump locations of Markov processes
• Bouncy Hybrid Sampler as a Unifying Device
• Generalizing Parallel Replica Dynamics: Trajectory Fragments, Asynchronous Computing, and PDMPs
• Necessary and sufficient symmetries in Event-Chain Monte Carlo with generalized flows and Application to hard dimers
• The Application of Zig-Zag Sampler in Sequential Markov Chain Monte Carlo