Coupling Control Variates for Markov Chain Monte Carlo

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.

References in corpus (2)

• Non equilibrium steady states: fluctuations and large deviations of the density and of the current
• Large deviations for a stochastic model of heat flow

Cited by in corpus (5)

• The computation of averages from equilibrium and nonequilibrium Langevin molecular dynamics
• Maximal couplings of the Metropolis-Hastings algorithm
• Coupling sample paths to the partial thermodynamic limit in stochastic chemical reaction networks
• Couplings of the Random-Walk Metropolis algorithm
• Hamiltonian Monte Carlo Swindles