Variable transformation to obtain geometric ergodicity in the random-walk Metropolis algorithm

DOI10.1214/12-AOS1048MaRDI QIDQ139529zbMATH OpenFDO

Authors Leif T. Johnson, Charles J. Geyer, Leif T. Johnson, Charles J. Geyer

Publication date 1 December 2012

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

Full work available at URL https://arxiv.org/abs/1302.6741, https://projecteuclid.org/euclid.aos/1361542074

zbMATH Keywords

Markov chain Monte Carloconjugate priorchange of variabledrift conditionexponential familyMarkov chain isomorphismMetropolis-Hastings-Green algorithm

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Monte Carlo methods (65C05) Discrete-time Markov processes on general state spaces (60J05)

Abstract: A random-walk Metropolis sampler is geometrically ergodic if its equilibrium density is super-exponentially light and satisfies a curvature condition [Stochastic Process. Appl. 85 (2000) 341-361]. Many applications, including Bayesian analysis with conjugate priors of logistic and Poisson regression and of log-linear models for categorical data result in posterior distributions that are not super-exponentially light. We show how to apply the change-of-variable formula for diffeomorphisms to obtain new densities that do satisfy the conditions for geometric ergodicity. Sampling the new variable and mapping the results back to the old gives a geometrically ergodic sampler for the original variable. This method of obtaining geometric ergodicity has very wide applicability.

Recommendations

• Geometric ergodicity of Metropolis algorithms
• The random walk Metropolis: linking theory and practice through a case study
• On the geometric ergodicity of hybrid samplers
• Geometric ergodicity of Gibbs and block Gibbs samplers for a hierarchical random effects model
• Necessary conditions for geometric and polynomial ergodicity of random-walk-type Markov chains

Cites work

• scientific article; zbMATH DE number 3644239 (Why is no real title available?)
• scientific article; zbMATH DE number 5954252 (Why is no real title available?)
• scientific article; zbMATH DE number 5520724 (Why is no real title available?)
• scientific article; zbMATH DE number 3710458 (Why is no real title available?)
• scientific article; zbMATH DE number 3602484 (Why is no real title available?)
• scientific article; zbMATH DE number 720750 (Why is no real title available?)
• scientific article; zbMATH DE number 1077338 (Why is no real title available?)
• scientific article; zbMATH DE number 1085989 (Why is no real title available?)
• scientific article; zbMATH DE number 840151 (Why is no real title available?)
• A general framework for the parametrization of hierarchical models
• Batch means and spectral variance estimators in Markov chain Monte Carlo
• Central limit theorem for additive functionals of reversible Markov processes and applications to simple exclusions
• Conjugate priors for exponential families
• General Irreducible Markov Chains and Non-Negative Operators
• General state space Markov chains and MCMC algorithms
• Geometric convergence and central limit theorems for multidimensional Hastings and Metropolis algorithms
• Geometric ergodicity and hybrid Markov chains
• Geometric ergodicity of Gibbs and block Gibbs samplers for a hierarchical random effects model
• Geometric ergodicity of Metropolis algorithms
• Gibbs sampling for a Bayesian hierarchical general linear model
• Handbook of Markov Chain Monte Carlo
• Markov Chains and Stochastic Stability
• Markov chains for exploring posterior distributions. (With discussion)
• Minorization Conditions and Convergence Rates for Markov Chain Monte Carlo
• Monte Carlo sampling methods using Markov chains and their applications
• Necessary conditions for geometric and polynomial ergodicity of random-walk-type Markov chains
• Nonasymptotic bounds on the mean square error for MCMC estimates via renewal techniques
• On the Markov chain central limit theorem
• On the central limit theorem for an ergodic Markov chain
• Polynomial convergence rates of Markov chains
• Rates of convergence of the Hastings and Metropolis algorithms
• Reversible jump Markov chain Monte Carlo computation and Bayesian model determination
• Rigorous confidence bounds for MCMC under a geometric drift condition
• Sampling-Based Approaches to Calculating Marginal Densities
• Stability of the Gibbs sampler for Bayesian hierarchical models
• Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
• Sufficient burn-in for Gibbs samplers for a hierarchical random effects model.
• The Calculation of Posterior Distributions by Data Augmentation
• Variational Analysis

Cited in

(13)

• Transport map accelerated Markov chain Monte Carlo
• Speed up Zig-Zag
• On the theoretical properties of the exchange algorithm
• Geometric ergodicity of Metropolis-Hastings algorithms for conditional simulation in generalized linear mixed models
• Ergodicity of Markov chain Monte Carlo with reversible proposal
• Efficient shape-constrained inference for the autocovariance sequence from a reversible Markov chain
• mcmc
• Geometric ergodicity of the bouncy particle sampler
• Exact convergence analysis for metropolis–hastings independence samplers in Wasserstein distances
• Bayesian inverse problems with \(l_1\) priors: a randomize-then-optimize approach
• Component-wise Markov chain Monte Carlo: uniform and geometric ergodicity under mixing and composition
• Deterministic Bayesian information fusion and the analysis of its performance
• Ergodicity of the zigzag process

Describes a project that uses

Uses Software

• mcmc

This page was built for publication: Variable transformation to obtain geometric ergodicity in the random-walk Metropolis algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q139529)