Optimal scaling of random walk Metropolis algorithms using Bayesian large-sample asymptotics

DOI10.1007/S11222-022-10080-8MaRDI QIDQ2128065zbMATH OpenOpenAlexFDO

Authors Sebastian M. Schmon, Philippe Gagnon

Publication date 21 April 2022

Published in Statistics and Computing (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/2104.06384

zbMATH Keywords

Bernstein-von Mises theoremlarge-sample theoryMarkov chain Monte Carlooptimal tuningweak convergence

Mathematics Subject Classification ID

Central limit and other weak theorems (60F05) Computational methods in Markov chains (60J22) Computational methods for problems pertaining to statistics (62-08) Bayesian inference (62F15) Monte Carlo methods (65C05)

Abstract: High-dimensional limit theorems have been shown useful to derive tuning rules for finding the optimal scaling in random-walk Metropolis algorithms. The assumptions under which weak convergence results are proved are however restrictive: the target density is typically assumed to be of a product form. Users may thus doubt the validity of such tuning rules in practical applications. In this paper, we shed some light on optimal-scaling problems from a different perspective, namely a large-sample one. This allows to prove weak convergence results under realistic assumptions and to propose novel parameter-dimension-dependent tuning guidelines. The proposed guidelines are consistent with previous ones when the target density is close to having a product form, and the results highlight that the correlation structure has to be accounted for to avoid performance deterioration if that is not the case, while justifying the use of a natural (asymptotically exact) approximation to the correlation matrix that can be employed for the very first algorithm run.

Recommendations

• Optimal scaling of random-walk Metropolis algorithms on general target distributions
• Weak convergence and optimal scaling of random walk Metropolis algorithms
• Optimal scaling for various Metropolis-Hastings algorithms.
• Optimal scaling of random walk Metropolis algorithms with discontinuous target densities
• Optimal scaling of Metropolis algorithms: Heading toward general target distributions

Cites work

• An adaptive Metropolis algorithm
• An automatic robust Bayesian approach to principal component regression
• Asymptotic Expansions Associated with Posterior Distributions
• Asymptotic normality of posterior distributions for exponential families when the number of parameters tends to infinity.
• Asymptotic Statistics
• Comparison methods for stochastic models and risks
• Equation of state calculations by fast computing machines
• Exponential convergence of Langevin distributions and their discrete approximations
• scientific article; zbMATH DE number 3083069 (Why is no real title available?)
• Informed reversible jump algorithms
• Large-sample asymptotics of the pseudo-marginal method
• Markov chains for exploring posterior distributions. (With discussion)
• Monte Carlo sampling from the quantum state space. I
• On convergence of posterior distributions
• On the computational complexity of MCMC-based estimators in large samples
• Optimal Scaling of Discrete Approximations to Langevin Diffusions
• Optimal scaling of random-walk Metropolis algorithms on general target distributions
• Optimal scaling of the random walk Metropolis algorithm under L^p mean differentiability
• Optimal scaling of the random walk Metropolis on elliptically symmetric unimodal targets
• Optimal tuning of the hybrid Monte Carlo algorithm
• Posterior inference in curved exponential families under increasing dimensions
• Regression. Models, methods and applications
• Scaling analysis of multiple-try MCMC methods
• Some contributions to the asymptotic theory of Bayes solutions
• The Bernstein-von Mises theorem under misspecification
• The correlated pseudomarginal method
• Weak convergence and optimal scaling of random walk Metropolis algorithms
• Weak convergence of Metropolis algorithms for non-I.I.D. target distributions

Cited in

(12)

• Optimal scaling for various Metropolis-Hastings algorithms.
• Asymptotic analysis of the random walk metropolis algorithm on ridged densities
• Optimal scaling of random-walk Metropolis algorithms on general target distributions
• Hierarchical models and tuning of random walk Metropolis algorithms
• Optimal scaling for the pseudo-marginal random walk Metropolis: insensitivity to the noise generating mechanism
• Optimal scaling of the random walk Metropolis algorithm under L^p mean differentiability
• Accelerating Bayesian inference for stochastic epidemic models using incidence data
• Optimal scaling of MCMC beyond Metropolis
• Black-box Bayesian inference for agent-based models
• An inequality for the total variation distance between high-dimensional centered Gaussian laws
• Bayesian analysis of spatial panel Durbin model with convex combinations of different spatial weight matrices
• On the optimal convergence rate for the Metropolis algorithm in one dimension

Describes a project that uses

Uses Software

• R

This page was built for publication: Optimal scaling of random walk Metropolis algorithms using Bayesian large-sample asymptotics

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2128065)