On a generalization of the preconditioned Crank-Nicolson Metropolis algorithm
arXiv:1504.03461 · doi:10.1007/s10208-016-9340-x
Abstract
Metropolis algorithms for approximate sampling of probability measures on infinite dimensional Hilbert spaces are considered and a generalization of the preconditioned Crank-Nicolson (pCN) proposal is introduced. The new proposal is able to incorporate information of the measure of interest. A numerical simulation of a Bayesian inverse problem indicates that a Metropolis algorithm with such a proposal performs independent of the state space dimension and the variance of the observational noise. Moreover, a qualitative convergence result is provided by a comparison argument for spectral gaps. In particular, it is shown that the generalization inherits geometric ergodicity from the Metropolis algorithm with pCN proposal.
40 pages, 3 Figures
References in corpus (2)
Cited by in corpus (24)
- Geometric MCMC for Infinite-Dimensional Inverse Problems
- Perturbation Bounds for Monte Carlo within Metropolis via Restricted Approximations
- Complexity Results for MCMC derived from Quantitative Bounds
- Adaptive Dimension Reduction to Accelerate Infinite-Dimensional Geometric Markov Chain Monte Carlo
- On the Consistency of Graph-based Bayesian Learning and the Scalability of Sampling Algorithms
- Multilevel Dimension-Independent Likelihood-Informed MCMC for Large-Scale Inverse Problems
- Hierarchical off-diagonal low-rank approximation of Hessians in inverse problems, with application to ice sheet model initializaiton
- Lithological Tomography with the Correlated Pseudo-Marginal Method
- Ensemble sampler for infinite-dimensional inverse problems
- Geometric convergence of elliptical slice sampling
- Variance-based sensitivity of Bayesian inverse problems to the prior distribution
- Dimension-independent Markov chain Monte Carlo on the sphere
- Dimension-free convergence rates for gradient Langevin dynamics in RKHS
- Scalable optimization-based sampling on function space
- Almost sure convergence rates of adaptive increasingly rare Markov chain Monte Carlo
- On an adaptive preconditioned Crank-Nicolson MCMC algorithm for infinite dimensional Bayesian inferences
- Multilevel Sequential Monte Carlo with Dimension-Independent Likelihood-Informed Proposals
- MALA-within-Gibbs samplers for high-dimensional distributions with sparse conditional structure
- hIPPYlib-MUQ: A Bayesian Inference Software Framework for Integration of Data with Complex Predictive Models under Uncertainty
- Local sensitivity analysis for Bayesian inverse problems
- Hierarchical surrogate-based Approximate Bayesian Computation for an electric motor test bench
- A hybrid adaptive MCMC algorithm in function spaces
- Optimization-Based MCMC Methods for Nonlinear Hierarchical Statistical Inverse Problems
- Bayesian inference and uncertainty quantification for image reconstruction with Poisson data