Optimal scaling of random walk Metropolis algorithms with discontinuous target densities

Abstract

We consider the optimal scaling problem for high-dimensional random walk Metropolis (RWM) algorithms where the target distribution has a discontinuous probability density function. Almost all previous analysis has focused upon continuous target densities. The main result is a weak convergence result as the dimensionality d of the target densities converges to infinity. In particular, when the proposal variance is scaled by $d^{-2}$, the sequence of stochastic processes formed by the first component of each Markov chain converges to an appropriate Langevin diffusion process. Therefore optimizing the efficiency of the RWM algorithm is equivalent to maximizing the speed of the limiting diffusion. This leads to an asymptotic optimal acceptance rate of $e^{-2}$ (=0.1353) under quite general conditions. The results have major practical implications for the implementation of RWM algorithms by highlighting the detrimental effect of choosing RWM algorithms over Metropolis-within-Gibbs algorithms.

arXiv commentPublished in at http://dx.doi.org/10.1214/11-AAP817 the Annals of Applied Probability (http://www.imstat.org/aap/) by the Institute of Mathematical Statistics (http://www.imstat.org)

References in corpus (3)

• Optimal scaling for partially updating MCMC algorithms
• Optimal scaling of the random walk Metropolis on elliptically symmetric unimodal targets
• Weak convergence of Metropolis algorithms for non-i.i.d. target distributions

Cited by in corpus (5)

• Optimal scaling for the transient phase of Metropolis Hastings algorithms: The longtime behavior
• Optimal scaling for the transient phase of the random walk Metropolis algorithm: The mean-field limit
• Comparison of hit-and-run, slice sampling and random walk Metropolis
• A Semiparametric Bayesian Model for Detecting Synchrony Among Multiple Neurons
• Sampling Constrained Continuous Probability Distributions: A Review