On the Computational Complexity of MCMC-based Estimators in Large Samples

Abstract

In this paper we examine the implications of the statistical large sample theory for the computational complexity of Bayesian and quasi-Bayesian estimation carried out using Metropolis random walks. Our analysis is motivated by the Laplace-Bernstein-Von Mises central limit theorem, which states that in large samples the posterior or quasi-posterior approaches a normal density. Using the conditions required for the central limit theorem to hold, we establish polynomial bounds on the computational complexity of general Metropolis random walks methods in large samples. Our analysis covers cases where the underlying log-likelihood or extremum criterion function is possibly non-concave, discontinuous, and with increasing parameter dimension. However, the central limit theorem restricts the deviations from continuity and log-concavity of the log-likelihood or extremum criterion function in a very specific manner. Under minimal assumptions required for the central limit theorem to hold under the increasing parameter dimension, we show that the Metropolis algorithm is theoretically efficient even for the canonical Gaussian walk which is studied in detail. Specifically, we show that the running time of the algorithm in large samples is bounded in probability by a polynomial in the parameter dimension $d$, and, in particular, is of stochastic order $d^2$ in the leading cases after the burn-in period. We then give applications to exponential families, curved exponential families, and Z-estimation of increasing dimension.

36 pages, 2 figures

References in corpus (1)

• An MCMC Approach to Classical Estimation

Cited by in corpus (11)

• Explicit error bounds for Markov chain Monte Carlo
• Quasi-Bayesian analysis of nonparametric instrumental variables models
• Scalable Importance Tempering and Bayesian Variable Selection
• Hit-and-run for numerical integration
• Explicit convergence bounds for Metropolis Markov chains: isoperimetry, spectral gaps and profiles
• Convergence rate of Markov chain methods for genomic motif discovery
• Error bounds of MCMC for functions with unbounded stationary variance
• On Oracle Property and Asymptotic Validity of Bayesian Generalized Method of Moments
• Computation of expectations by Markov chain Monte Carlo methods
• Local Consistency of Markov Chain Monte Carlo Methods
• Machine Learning for Complex Systems with Abnormal Pattern by Exception Maximization Outlier Detection Method