Optimal scalings for local Metropolis-Hastings chains on nonproduct targets in high dimensions

DOI10.1214/08-AAP563zbMATH Open1172.60328arXiv0908.0865MaRDI QIDQ2389596FDOQ2389596

A. M. Stuart, Gareth O. Roberts, Alexandros Beskos

Publication date: 17 July 2009

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

Abstract: We investigate local MCMC algorithms, namely the random-walk Metropolis and the Langevin algorithms, and identify the optimal choice of the local step-size as a function of the dimension $n$ of the state space, asymptotically as $noinfty$. We consider target distributions defined as a change of measure from a product law. Such structures arise, for instance, in inverse problems or Bayesian contexts when a product prior is combined with the likelihood. We state analytical results on the asymptotic behavior of the algorithms under general conditions on the change of measure. Our theory is motivated by applications on conditioned diffusion processes and inverse problems related to the 2D Navier--Stokes equation.

Full work available at URL: https://arxiv.org/abs/0908.0865

zbMATH Keywords

Langevindiffusion[https://portal.mardi4nfdi.de/w/index.php?title=+Special%3ASearch&search=Karhunen-Lo%EF%BF%BD%EF%BF%BDve&go=Go Karhunen-Lo��ve]Gaussian law on Hilbert spaceNavier-Stokes PDErandom-walk Metropolissquared-jump-distance

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Numerical analysis or methods applied to Markov chains (65C40)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Weak convergence and optimal scaling of random walk Metropolis algorithms
• Monte Carlo sampling methods using Markov chains and their applications
• Stochastic Equations in Infinite Dimensions
• Optimal Scaling of Discrete Approximations to Langevin Diffusions
• Infinite-dimensional dynamical systems. An introduction to dissipative parabolic PDEs and the theory of global attractors
• Analysis of SPDEs arising in path sampling. I: The Gaussian case
• Optimal scaling of the random walk Metropolis on elliptically symmetric unimodal targets
• Optimal acceptance rates for Metropolis algorithms: Moving beyond 0.234
• MCMC METHODS FOR DIFFUSION BRIDGES
• Scaling Limits for the Transient Phase of Local Metropolis–Hastings Algorithms
• From Metropolis to diffusions: Gibbs states and optimal scaling.
• Optimal scaling of MaLa for nonlinear regression.
• Weak convergence of Metropolis algorithms for non-I.I.D. target distributions
• Optimal scaling of Metropolis algorithms: Heading toward general target distributions
• Simulation of conditioned diffusion and application to parameter estimation
• Optimal scaling for partially updating MCMC algorithms

Cited In (43)

• Scaling analysis of delayed rejection MCMC methods
• Optimal tuning of the hybrid Monte Carlo algorithm
• Approximate large-scale Bayesian spatial modeling with application to quantitative magnetic resonance imaging
• Large-Scale Bayesian Spatial-Temporal Regression with Application to Cardiac MR-Perfusion Imaging
• Efficiency of delayed-acceptance random walk metropolis algorithms
• Asymptotic analysis of the random walk metropolis algorithm on ridged densities
• Optimal Scaling of the Random Walk Metropolis: General Criteria for the 0.234 Acceptance Rule
• On the stability of sequential Monte Carlo methods in high dimensions
• Designing simple and efficient Markov chain Monte Carlo proposal kernels
• An adaptive multiple-try Metropolis algorithm
• On the convergence of adaptive sequential Monte Carlo methods
• Diffusion limits of the random walk Metropolis algorithm in high dimensions
• Optimal strategies for the control of autonomous vehicles in data assimilation
• Minimising MCMC variance via diffusion limits, with an application to simulated tempering
• Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions
• Bayesian computation: a summary of the current state, and samples backwards and forwards
• Optimal scaling of random-walk Metropolis algorithms on general target distributions
• Accelerated dimension-independent adaptive metropolis
• On the efficiency of pseudo-marginal random walk Metropolis algorithms
• Some Remarks on Preconditioning Molecular Dynamics
• Hierarchical models: local proposal variances for RWM-within-Gibbs and MALA-within-Gibbs
• Efficient strategy for the Markov chain Monte Carlo in high-dimension with heavy-tailed target probability distribution
• Uncertainty Quantification in Graph-Based Classification of High Dimensional Data
• Optimal scaling for the transient phase of Metropolis Hastings algorithms: the longtime behavior
• Convergence of unadjusted Hamiltonian Monte Carlo for mean-field models
• Localization for MCMC: sampling high-dimensional posterior distributions with local structure
• A blocking scheme for dimension-robust Gibbs sampling in large-scale image deblurring
• A Bayesian Approach to Estimating Background Flows from a Passive Scalar
• Weak convergence and optimal tuning of the reversible jump algorithm
• Decreasing Flow Uncertainty in Bayesian Inverse Problems Through Lagrangian Drifter Control
• Hybrid Monte Carlo on Hilbert spaces
• Anytime parallel tempering
• Sequential Monte Carlo methods for Bayesian elliptic inverse problems
• Random walk Metropolis algorithm in high dimension with non-Gaussian target distributions
• An Adaptive Independence Sampler MCMC Algorithm for Bayesian Inferences of Functions
• Optimal scaling of the random walk Metropolis algorithm under L^p mean differentiability
• Hierarchical models and tuning of random walk Metropolis algorithms
• Optimal scaling and diffusion limits for the Langevin algorithm in high dimensions
• MALA-within-Gibbs Samplers for High-Dimensional Distributions with Sparse Conditional Structure
• Asymptotic variance for random walk Metropolis chains in high dimensions: logarithmic growth via the Poisson equation
• Optimal scaling for the transient phase of the random walk Metropolis algorithm: the mean-field limit
• On an adaptive preconditioned Crank-Nicolson MCMC algorithm for infinite dimensional Bayesian inference
• Scaling Up Bayesian Uncertainty Quantification for Inverse Problems Using Deep Neural Networks

This page was built for publication: Optimal scalings for local Metropolis-Hastings chains on nonproduct targets in high dimensions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2389596)