On the computational complexity of MCMC-based estimators in large samples

DOI10.1214/08-AOS634zbMath1175.65015arXiv0704.2167MaRDI QIDQ2388988

Victor Chernozhukov, Alexandre Belloni

Publication date: 22 July 2009

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/0704.2167

zbMATH Keywords

computational complexity; increasing dimension; Monte-Carlo integration; Markov chain Monte Carlo (MCMC) method; Bayesian and quasi-Bayesian inference; Metropolis random walk

Mathematics Subject Classification ID

60J22: Computational methods in Markov chains

62F15: Bayesian inference

62M05: Markov processes: estimation; hidden Markov models

65C05: Monte Carlo methods

60G50: Sums of independent random variables; random walks

65C40: Numerical analysis or methods applied to Markov chains

65Y20: Complexity and performance of numerical algorithms

Related Items

Computation of Expectations by Markov Chain Monte Carlo Methods, Additive models for quantile regression: model selection and confidence bands, Convergence rate of Markov chain methods for genomic motif discovery, Error bounds of MCMC for functions with unbounded stationary variance, \(\ell_1\)-penalized quantile regression in high-dimensional sparse models, Local consistency of Markov chain Monte Carlo methods, Rejoinder on: ``Local quantile regression, Quasi-Bayesian analysis of nonparametric instrumental variables models, Hit-and-Run for Numerical Integration, EFFICIENCY IN LARGE DYNAMIC PANEL MODELS WITH COMMON FACTORS, GENERAL INEQUALITIES FOR GIBBS POSTERIOR WITH NONADDITIVE EMPIRICAL RISK

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Central limit theorem for additive functionals of reversible Markov processes and applications to simple exclusions
• Asymptotic behavior of likelihood methods for exponential families when the number of parameters tends to infinity
• The geometry of exponential families
• Sharper bounds for Gaussian and empirical processes
• Sampling from log-concave distributions
• Exponential convergence of Langevin distributions and their discrete approximations
• Weak convergence and optimal scaling of random walk Metropolis algorithms
• Polynomial splines and their tensor products in extended linear modeling. (With discussions)
• An MCMC approach to classical estimation.
• Empirical likelihood estimation and consistent tests with conditional moment restrictions
• Optimal scaling for various Metropolis-Hastings algorithms.
• On parameters of increasing dimensions
• Asymptotic normality of posterior distributions for exponential families when the number of parameters tends to infinity.
• Asymptotic behavior of Bayes estimates under possibly incorrect models
• Asymptotic efficiency in estimation with conditional moment restrictions
• Robust regression: Asymptotics, conjectures and Monte Carlo
• Choosing sample path length and number of sample paths when starting in steady state
• Isoperimetric problems for convex bodies and a localization lemma
• Weak convergence and empirical processes. With applications to statistics
• Langevin-type models. I: Diffusions with given stationary distributions and their discretizations
• Hit-and-run mixes fast
• An adaptive version for the Metropolis adjusted Langevin algorithm with a truncated drift
• Approximating the Permanent
• The geometry of logconcave functions and sampling algorithms
• Implementation of Estimating Function-Based Inference Procedures With Markov Chain Monte Carlo Samplers
• Generalized Instrumental Variables Estimation of Nonlinear Rational Expectations Models
• Random walks in a convex body and an improved volume algorithm
• One-Step Estimators for Over-Identified Generalized Method of Moments Models
• Asymptotic Normality of Semiparametric and Nonparametric Posterior Distributions
• Hit-and-Run from a Corner
• Some contributions to the asymptotic theory of Bayes solutions
• Monte Carlo strategies in scientific computing