Kinetic walks for sampling

MaRDI QIDQ5114800zbMATH OpenFDO

Authors Pierre Monmarché

Publication date 26 June 2020

Full work available at URL https://arxiv.org/abs/1903.00550, http://alea.impa.br/articles/v17/17-20.pdf

zbMATH Keywords

MCMCzig-zag processnon-reversible sampling

Mathematics Subject Classification ID

Numerical analysis or methods applied to Markov chains (65C40) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10)

Abstract: The persistent walk is a classical model in kinetic theory, which has also been studied as a toy model for MCMC questions. Its continuous limit, the telegraph process, has recently been extended to various velocity jump processes (Bouncy Particle Sampler, Zig-Zag process, etc.) in order to sample general target distributions on $mathbb{R}^d$. This paper studies, from a sampling point of view, general kinetic walks that are natural discrete-time (and possibly discrete-space) counterparts of these continuous-space processes. The main contributions of the paper are the definition and study of a discrete-space Zig-Zag sampler and the definition and time-discretisation of hybrid jump/diffusion kinetic samplers for multi-scale potentials on $mathbb{R}^d$.

Recommendations

• Dynamical sampling with moving devices
• Premature sampling in random walks
• Kendall random walks
• Walking randomly, massively, and efficiently
• Exact and efficient sampling of conditioned walks
• Generalized atmospheric sampling of self-avoiding walks
• Sampling rate effects on measurements of correlated and biased random walks
• Structural, Syntactic, and Statistical Pattern Recognition
• scientific article; zbMATH DE number 1827973

Cites work

• scientific article; zbMATH DE number 3644239 (Why is no real title available?)
• scientific article; zbMATH DE number 599596 (Why is no real title available?)
• A Diffusion Limit for Generalized Correlated Random Walks
• A Liapounov bound for solutions of the Poisson equation
• A piecewise deterministic scaling limit of lifted Metropolis-Hastings in the Curie-Weiss model
• A stochastic model related to the telegrapher's equation
• Analysis of a nonreversible Markov chain sampler.
• Convergence of numerical time-averaging and stationary measures via Poisson equations
• Detailed spectral study of processes that are less hesistent than others
• Ergodicity of the zigzag process
• Exact simulation of the jump times of a class of piecewise deterministic Markov processes
• Expansion of the global error for numerical schemes solving stochastic differential equations
• Foundations of Modern Probability
• From persistent random walk to the telegraph noise
• Geometric numerical integration illustrated by the Störmer–Verlet method
• Hypocoercivity without confinement
• Irreversible Monte Carlo algorithms for efficient sampling
• Limit theorems for the zig-zag process
• Long time behavior of telegraph processes under convex potentials
• Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
• Nonhomogeneous geometric distributions with relations to birth and death processes
• ON DIFFUSION BY DISCONTINUOUS MOVEMENTS, AND ON THE TELEGRAPH EQUATION
• On the spectral analysis of second-order Markov chains
• Partial differential equations and stochastic methods in molecular dynamics
• Partite saturation problems
• Piecewise deterministic simulated annealing
• Rational construction of stochastic numerical methods for molecular sampling
• The Bouncy Particle Sampler: A Non-Reversible Rejection-Free Markov Chain Monte Carlo Method
• The computation of averages from equilibrium and nonequilibrium Langevin molecular dynamics
• The general correlated random walk
• The one-dimensional asymmetric persistent random walk
• The zig-zag process and super-efficient sampling for Bayesian analysis of big data
• Weakly self-interacting velocity jump processes for bacterial chemotaxis and adaptive algorithms
• Yet Another Look at Harris’ Ergodic Theorem for Markov Chains

Cited in

(2)

• High-dimensional MCMC with a standard splitting scheme for the underdamped Langevin diffusion
• Exact targeting of Gibbs distributions using velocity-jump processes

This page was built for publication: Kinetic walks for sampling

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5114800)