Coupling control variates for Markov chain Monte Carlo

DOI10.1016/J.JCP.2009.03.043MaRDI QIDQ732966zbMATH OpenOpenAlexFDO

Authors Jonathan Goodman, Kevin K. Lin

Publication date 15 October 2009

Published in Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/0809.2300

zbMATH Keywords

control variatesnumerical examplesvariance reductionMarkov chain Monte Carlo methodcouplingMonte Carlo integrationnonequilibrium statistical mechanicsnonequilibrium transport

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Monte Carlo methods (65C05) Numerical analysis or methods applied to Markov chains (65C40) Transport processes in time-dependent statistical mechanics (82C70)

Abstract: We show that Markov couplings can be used to improve the accuracy of Markov chain Monte Carlo calculations in some situations where the steady-state probability distribution is not explicitly known. The technique generalizes the notion of control variates from classical Monte Carlo integration. We illustrate it using two models of nonequilibrium transport.

Recommendations

• Constructing sampling schemes via coupling: Markov semigroups and optimal transport
• Control Variates for Estimation Based on Reversible Markov Chain Monte Carlo Samplers
• scientific article; zbMATH DE number 1195782
• Efficient Simulation via Coupling
• Over-relaxation methods and coupled Markov chains for Monte Carlo simulation

Cites work

• scientific article; zbMATH DE number 4070125 (Why is no real title available?)
• scientific article; zbMATH DE number 1124118 (Why is no real title available?)
• scientific article; zbMATH DE number 6818309 (Why is no real title available?)
• scientific article; zbMATH DE number 797399 (Why is no real title available?)
• scientific article; zbMATH DE number 3357844 (Why is no real title available?)
• scientific article; zbMATH DE number 3196612 (Why is no real title available?)
• A simple coupling of renewal processes
• Approximating Martingales for Variance Reduction in Markov Process Simulation
• Correlations in nonequilibrium steady states of random halves models
• Efficient Simulation via Coupling
• Exact sampling with coupled Markov chains and applications to statistical mechanics
• Large deviations for a stochastic model of heat flow
• Likelihood ratio gradient estimation for stochastic recursions
• Non-equilibrium steady states: fluctuations and large deviations of the density and of the current
• On isotropic brownian motions
• Regenerative structure of Markov chains simulated via common random numbers
• Shadow hybrid Monte Carlo: an efficient propagator in phase space of macromolecules

Cited in

(7)

• Partial differential equations and stochastic methods in molecular dynamics
• Coupling sample paths to the thermodynamic limit in Monte Carlo estimators with applications to gene expression
• A Perturbative Approach to Control Variates in Molecular Dynamics
• Variance reduction through smoothing and control variates for Markov chain simulations
• Control Variates for the Metropolis–Hastings Algorithm
• Metropolis-Hastings transition kernel couplings
• Constructing sampling schemes via coupling: Markov semigroups and optimal transport

This page was built for publication: Coupling control variates for Markov chain Monte Carlo

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q732966)