High-dimensional scaling limits of piecewise deterministic sampling algorithms

DOI10.1214/21-AAP1762MaRDI QIDQ2094570zbMATH OpenFDO

Authors Joris Bierkens, Kengo Kamatani, Gareth O. Roberts

Publication date 31 October 2022

Published in The Annals of Applied Probability (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1807.11358

zbMATH Keywords

exponential ergodicityGaussian processMarkov chain Monte Carlopiecewise deterministic Markov processesweak convergence

Mathematics Subject Classification ID

Central limit and other weak theorems (60F05) Monte Carlo methods (65C05)

Abstract: Piecewise deterministic Markov processes are an important new tool in the design of Markov Chain Monte Carlo algorithms. Two examples of fundamental importance are the Bouncy Particle Sampler (BPS) and the Zig-Zag process (ZZ). In this paper scaling limits for both algorithms are determined. Here the dimensionality of the space tends towards infinity and the target distribution is the multivariate standard normal distribution. For several quantities of interest (angular momentum, first coordinate, and negative log-density) the scaling limits show qualitatively very different and rich behaviour. Based on these scaling limits the performance of the two algorithms in high dimensions can be compared. Although for angular momentum both processes require only a computational effort of $O(d)$ to obtain approximately independent samples, the computational effort for negative log-density and first coordinate differ: for these BPS requires $O(d^2)$ computational effort whereas ZZ requires $O(d)$. Finally we provide a criterion for the choice of the refreshment rate of BPS.

Recommendations

• Adaptive schemes for piecewise deterministic Monte Carlo algorithms
• Randomized Hamiltonian Monte Carlo as scaling limit of the bouncy particle sampler and dimension-free convergence rates
• Hypocoercivity of piecewise deterministic Markov process-Monte Carlo
• Infinite dimensional piecewise deterministic Markov processes
• Limit theorems for the zig-zag process

Cites work

• A dozen de Finetti-style results in search of a theory
• A piecewise deterministic Monte Carlo method for diffusion bridges
• Central limit theorems in D[0, 1]
• Complexity bounds for Markov chain Monte Carlo algorithms via diffusion limits
• Coordinate sampler: a non-reversible Gibbs-like MCMC sampler
• Efficient strategy for the Markov chain Monte Carlo in high-dimension with heavy-tailed target probability distribution
• Equivalence of Stochastic Equations and Martingale Problems
• Ergodicity of the zigzag process
• Exponential and uniform ergodicity of Markov processes
• Exponential ergodicity of the bouncy particle sampler
• Fluctuations of the empirical measure of freezing Markov chains
• scientific article; zbMATH DE number 3901778 (Why is no real title available?)
• scientific article; zbMATH DE number 3951715 (Why is no real title available?)
• scientific article; zbMATH DE number 43057 (Why is no real title available?)
• scientific article; zbMATH DE number 51724 (Why is no real title available?)
• scientific article; zbMATH DE number 1245556 (Why is no real title available?)
• scientific article; zbMATH DE number 1354815 (Why is no real title available?)
• scientific article; zbMATH DE number 1834045 (Why is no real title available?)
• scientific article; zbMATH DE number 3085434 (Why is no real title available?)
• Hypocoercivity of piecewise deterministic Markov process-Monte Carlo
• Limit theorems for the zig-zag process
• Long time behavior of telegraph processes under convex potentials
• Markov Processes, Gaussian Processes, and Local Times
• Normal Approximation by Stein’s Method
• Normal approximations with Malliavin calculus. From Stein's method to universality
• Optimal scaling for various Metropolis-Hastings algorithms.
• Stability and Ergodicity of Piecewise Deterministic Markov Processes
• The Bouncy Particle Sampler: A Non-Reversible Rejection-Free Markov Chain Monte Carlo Method
• The zig-zag process and super-efficient sampling for Bayesian analysis of big data
• Weak convergence and optimal scaling of random walk Metropolis algorithms

Cited in

(19)

• Large deviations for the empirical measure of the zig-zag process
• On explicit \(L^2\)-convergence rate estimate for piecewise deterministic Markov processes in MCMC algorithms
• Optimal convergence rates of high order Parzen windows with unbounded sampling
• Ergodicity of the zigzag process
• Adaptive schemes for piecewise deterministic Monte Carlo algorithms
• Approximating Large Frequency Moments with Pick-and-Drop Sampling
• Analysis of high-dimensional continuous time Markov chains using the local bouncy particle sampler
• On Unifying the Space of ℓ₀-Sampling Algorithms
• The Moser-Tardos Resample algorithm: Where is the limit? (an experimental inquiry)
• Limit theorems for the zig-zag process
• Infinite dimensional piecewise deterministic Markov processes
• Polynomial convergence rates of piecewise deterministic Markov processes
• Sampling algorithms in statistical physics: a guide for statistics and machine learning
• Posterior computation with the Gibbs zig-zag sampler
• Zigzag Path Connects Two Monte Carlo Samplers: Hamiltonian Counterpart to a Piecewise Deterministic Markov Process
• Scaling of piecewise deterministic Monte Carlo for anisotropic targets
• Stereographic Markov chain Monte Carlo
• Windowed thinning and query complexity for the bouncy particle and Zigzag samplers
• Piecewise deterministic sampling with splitting schemes

This page was built for publication: High-dimensional scaling limits of piecewise deterministic sampling algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2094570)