Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions

DOI10.1214/13-AAP982zbMath1307.65002arXiv1112.1392WikidataQ56894224 ScholiaQ56894224MaRDI QIDQ473164

Andrew M. Stuart, Martin Hairer, Sebastian J. Vollmer

Publication date: 21 November 2014

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

Full work available at URL: https://arxiv.org/abs/1112.1392

zbMATH Keywords

random walk; Metropolis-Hastings algorithm; Gaussian random field; \(L^{2}\)-spectral gaps; Markov chain Monte Carlo in infinite dimensions; sampling algorithm; Wasserstein spectral gaps; weak Harris theorem

Mathematics Subject Classification ID

60J22: Computational methods in Markov chains

60G60: Random fields

65C05: Monte Carlo methods

60G50: Sums of independent random variables; random walks

65C40: Numerical analysis or methods applied to Markov chains

Related Items

Quantitative Harris-type theorems for diffusions and McKean–Vlasov processes, Ergodicity of Markov chain Monte Carlo with reversible proposal, Unnamed Item, Multilevel Markov Chain Monte Carlo for Bayesian Inversion of Parabolic Partial Differential Equations under Gaussian Prior, Analysis of a multilevel Markov chain Monte Carlo finite element method for Bayesian inversion of log-normal diffusions, Unnamed Item, Consistency of Bayesian inference with Gaussian process priors for a parabolic inverse problem, Bayesian Imaging with Data-Driven Priors Encoded by Neural Networks, Bayesian Inference and Uncertainty Quantification for Medical Image Reconstruction with Poisson Data, Consistency of Bayesian inference with Gaussian process priors in an elliptic inverse problem, A Bayesian Approach to Estimating Background Flows from a Passive Scalar, Reconciling Bayesian and Perimeter Regularization for Binary Inversion, Non-stationary multi-layered Gaussian priors for Bayesian inversion, Multilevel Markov Chain Monte Carlo, Simulation from quasi-stationary distributions on reducible state spaces, MCMC for Imbalanced Categorical Data, Quantitative bounds of convergence for geometrically ergodic Markov chain in the Wasserstein distance with application to the Metropolis adjusted Langevin algorithm, Sequential Monte Carlo methods for Bayesian elliptic inverse problems, MCMC methods for functions: modifying old algorithms to make them faster, Optimal experimental design for infinite-dimensional Bayesian inverse problems governed by PDEs: a review, VI-DGP: a variational inference method with deep generative prior for solving high-dimensional inverse problems, Bayesian inversion of log-normal eikonal equations, Spectral gaps and error estimates for infinite-dimensional Metropolis-Hastings with non-Gaussian priors, Laplace priors and spatial inhomogeneity in Bayesian inverse problems, Error control of the numerical posterior with Bayes factors in Bayesian uncertainty quantification, On the accept-reject mechanism for Metropolis-Hastings algorithms, Dimension‐independent Markov chain Monte Carlo on the sphere, A Bayesian approach for consistent reconstruction of inclusions, Transform MCMC schemes for sampling intractable factor copula models, Convergence of unadjusted Hamiltonian Monte Carlo for mean-field models, Multilevel dimension-independent likelihood-informed MCMC for large-scale inverse problems, Exact convergence analysis for metropolis–hastings independence samplers in Wasserstein distances, On some information-theoretic aspects of non-linear statistical inverse problems, Exponential stability of slowly decaying solutions to the kinetic-Fokker-Planck equation, The Bayesian formulation of EIT: analysis and algorithms, Markov chain Monte Carlo and irreversibility, On statistical Calderón problems, Ruelle-Pollicott resonances of stochastic systems in reduced state space. Part I: Theory, Geometric MCMC for infinite-dimensional inverse problems, Explicit contraction rates for a class of degenerate and infinite-dimensional diffusions, Hierarchical Bayesian level set inversion, Perturbation theory for Markov chains via Wasserstein distance, Efficient strategy for the Markov chain Monte Carlo in high-dimension with heavy-tailed target probability distribution, On a generalization of the preconditioned Crank-Nicolson metropolis algorithm, Bayesian inversion of a diffusion model with application to biology, Two-scale coupling for preconditioned Hamiltonian Monte Carlo in infinite dimensions, Ensemble sampler for infinite-dimensional inverse problems, Generalized parallel tempering on Bayesian inverse problems, Statistical guarantees for Bayesian uncertainty quantification in nonlinear inverse problems with Gaussian process priors, Randomized Hamiltonian Monte Carlo as scaling limit of the bouncy particle sampler and dimension-free convergence rates, Mixing rates for Hamiltonian Monte Carlo algorithms in finite and infinite dimensions, Continuum limit and preconditioned Langevin sampling of the path integral molecular dynamics, Bayesian multiscale deep generative model for the solution of high-dimensional inverse problems, Geometric convergence bounds for Markov chains in Wasserstein distance based on generalized drift and contraction conditions, Strict Kantorovich contractions for Markov chains and Euler schemes with general noise, Spectral gap of replica exchange Langevin diffusion on mixture distributions, Localization for MCMC: sampling high-dimensional posterior distributions with local structure, Bayesian-based predictions of COVID-19 evolution in Texas using multispecies mixture-theoretic continuum models, A probabilistic finite element method based on random meshes: a posteriori error estimators and Bayesian inverse problems, On the limitations of single-step drift and minorization in Markov chain convergence analysis, Proposals which speed up function-space MCMC, Measuring sample quality with diffusions, Metropolis-Hastings reversiblizations of non-reversible Markov chains, Exponential ergodicity for Markov processes with random switching, Dimension-independent likelihood-informed MCMC, Efficient parameter estimation for a methane hydrate model with active subspaces, Error bounds for Metropolis-Hastings algorithms applied to perturbations of Gaussian measures in high dimensions, Quantitative contraction rates for Markov chains on general state spaces, Bayesian neural network priors for edge-preserving inversion, Multilevel Markov chain Monte Carlo for Bayesian inverse problem for Navier-Stokes equation, Dimension-Independent MCMC Sampling for Inverse Problems with Non-Gaussian Priors, MALA-within-Gibbs Samplers for High-Dimensional Distributions with Sparse Conditional Structure, A Hierarchical Multilevel Markov Chain Monte Carlo Algorithm with Applications to Uncertainty Quantification in Subsurface Flow, Algorithms for Kullback--Leibler Approximation of Probability Measures in Infinite Dimensions

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Central limit theorem for Markov processes with spectral gap in the Wasserstein metric
• Diffusion limits of the random walk Metropolis algorithm in high dimensions
• Besov priors for Bayesian inverse problems
• Curvature, concentration and error estimates for Markov chain Monte Carlo
• Rigorous confidence bounds for MCMC under a geometric drift condition
• Markov chains and stochastic stability
• Asymptotic coupling and a general form of Harris' theorem with applications to stochastic delay equations
• Hybrid Monte Carlo on Hilbert spaces
• Pointwise ergodic theorems with rate and application to the CLT for Markov chains
• Geometric bounds for eigenvalues of Markov chains
• Central limit theorem for additive functionals of reversible Markov processes and applications to simple exclusions
• Approximate counting, uniform generation and rapidly mixing Markov chains
• A note on Metropolis-Hastings kernels for general state spaces
• Functional inequalities for the decay of sub-Markov semigroups
• Markov chains for exploring posterior distributions. (With discussion)
• Advanced MCMC methods for sampling on diffusion pathspace
• CLTs and asymptotic variance of time-sampled Markov chains
• Discretization-invariant Bayesian inversion and Besov space priors
• Optimal scalings for local Metropolis-Hastings chains on nonproduct targets in high dimensions
• Error bounds for Metropolis-Hastings algorithms applied to perturbations of Gaussian measures in high dimensions
• Monte Carlo strategies in scientific computing.
• Analysis of SPDEs arising in path sampling. II: The nonlinear case
• Sparse deterministic approximation of Bayesian inverse problems
• Inverse problems: A Bayesian perspective
• Explicit error bounds for Markov chain Monte Carlo
• Uncertainty Quantification and Weak Approximation of an Elliptic Inverse Problem
• Bounds on the L 2 Spectrum for Markov Chains and Markov Processes: A Generalization of Cheeger's Inequality
• MCMC METHODS FOR DIFFUSION BRIDGES
• Bayesian Nonparametrics
• A simple framework to justify linear response theory
• Geometric convergence and central limit theorems for multidimensional Hastings and Metropolis algorithms
• A splitting technique for Harris recurrent Markov chains
• A New Approach to the Limit Theory of Recurrent Markov Chains
• On the small balls problem for equivalent Gaussian measures
• Random walks in a convex body and an improved volume algorithm
• Annealing Markov Chain Monte Carlo with Applications to Ancestral Inference
• Monte Carlo sampling methods using Markov chains and their applications
• Weak Poincaré inequalities and \(L^2\)-convergence rates of Markov semigroups
• MCMC methods for functions: modifying old algorithms to make them faster
• Stochastic Equations in Infinite Dimensions