Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions
arXiv:1112.1392 · doi:10.1214/13-AAP982
Abstract
We study the problem of sampling high and infinite dimensional target measures arising in applications such as conditioned diffusions and inverse problems. We focus on those that arise from approximating measures on Hilbert spaces defined via a density with respect to a Gaussian reference measure. We consider the Metropolis-Hastings algorithm that adds an accept-reject mechanism to a Markov chain proposal in order to make the chain reversible with respect to the target measure. We focus on cases where the proposal is either a Gaussian random walk (RWM) with covariance equal to that of the reference measure or an Ornstein-Uhlenbeck proposal (pCN) for which the reference measure is invariant. Previous results in terms of scaling and diffusion limits suggested that the pCN has a convergence rate that is independent of the dimension while the RWM method has undesirable dimension-dependent behaviour. We confirm this claim by exhibiting a dimension-independent Wasserstein spectral gap for pCN algorithm for a large class of target measures. In our setting this Wasserstein spectral gap implies an -spectral gap. We use both spectral gaps to show that the ergodic average satisfies a strong law of large numbers, the central limit theorem and nonasymptotic bounds on the mean square error, all dimension independent. In contrast we show that the spectral gap of the RWM algorithm applied to the reference measures degenerates as the dimension tends to infinity.
Published in at http://dx.doi.org/10.1214/13-AAP982 the Annals of Applied Probability (http://www.imstat.org/aap/) by the Institute of Mathematical Statistics (http://www.imstat.org)
References in corpus (3)
Cited by in corpus (26)
- Statistical Aspects of Wasserstein Distances
- Dimension-independent likelihood-informed MCMC
- Geometric MCMC for Infinite-Dimensional Inverse Problems
- Exponential ergodicity for Markov processes with random switching
- On a generalization of the preconditioned Crank-Nicolson Metropolis algorithm
- Ruelle-Pollicott Resonances of Stochastic Systems in Reduced State Space. Part I: Theory
- Bayesian multiscale deep generative model for the solution of high-dimensional inverse problems
- Error bounds for Metropolis-Hastings algorithms applied to perturbations of Gaussian measures in high dimensions
- Efficient moment calculations for variance components in large unbalanced crossed random effects models
- Convergence of unadjusted Hamiltonian Monte Carlo for mean-field models
- A probabilistic finite element method based on random meshes: Error estimators and Bayesian inverse problems
- Explicit convergence bounds for Metropolis Markov chains: isoperimetry, spectral gaps and profiles
- Consistency of Bayesian inference with Gaussian process priors for a parabolic inverse problem
- Efficient parameter estimation for a methane hydrate model with active subspaces
- Two-scale coupling for preconditioned Hamiltonian Monte Carlo in infinite dimensions
- Generalized Parallel Tempering on Bayesian Inverse Problems
- Metropolis-Hastings reversiblizations of non-reversible Markov chains
- MCMC Methods for Functions: Modifying Old Algorithms to Make Them Faster
- Explicit contraction rates for a class of degenerate and infinite-dimensional diffusions
- Ensemble sampler for infinite-dimensional inverse problems
- Dimension-independent Markov chain Monte Carlo on the sphere
- Mixing of Metropolis-Adjusted Markov Chains via Couplings: The High Acceptance Regime
- Almost sure convergence rates of adaptive increasingly rare Markov chain Monte Carlo
- Convergence Speed and Approximation Accuracy of Numerical MCMC
- Sequential Kalman Tuning of the -preconditioned Crank-Nicolson algorithm: efficient, adaptive and gradient-free inference for Bayesian inverse problems
- Optimal convergence rates of MCMC integration for functions with unbounded second moment