Spectral gaps and error estimates for infinite-dimensional Metropolis-Hastings with non-Gaussian priors
From MaRDI portal
Publication:6104013
Abstract: We study a class of Metropolis-Hastings algorithms for target measures that are absolutely continuous with respect to a large class of non-Gaussian prior measures on Banach spaces. The algorithm is shown to have a spectral gap in a Wasserstein-like semimetric weighted by a Lyapunov function. A number of error bounds are given for computationally tractable approximations of the algorithm including bounds on the closeness of Ces'aro averages and other pathwise quantities via perturbation theory. Several applications illustrate the breadth of problems to which the results apply such as various likelihood approximations and perturbations of prior measures.
Recommendations
- Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions
- Two Metropolis--Hastings Algorithms for Posterior Measures with Non-Gaussian Priors in Infinite Dimensions
- Error bounds for Metropolis-Hastings algorithms applied to perturbations of Gaussian measures in high dimensions
- scientific article; zbMATH DE number 1500599
- Nonasymptotic bounds on the estimation error of MCMC algorithms
- A computable bound of the essential spectral radius of finite range metropolis-Hastings kernels
- The spectrum of the independent Metropolis-Hastings algorithm
- On inference for partially observed nonlinear diffusion models using the Metropolis-Hastings algorithm
- Non-asymptotic error bounds for sequential MCMC methods
Cites work
- A Liapounov bound for solutions of the Poisson equation
- Asymptotic coupling and a general form of Harris' theorem with applications to stochastic delay equations
- Besov priors for Bayesian inverse problems
- Computational Methods for Inverse Problems
- Convergence of numerical time-averaging and stationary measures via Poisson equations
- Diffusion limits of the random walk Metropolis algorithm in high dimensions
- Fast mixing of Metropolis-Hastings with unimodal targets
- Geometric analysis for the Metropolis algorithm on Lipschitz domains
- Geometric convergence and central limit theorems for multidimensional Hastings and Metropolis algorithms
- Geometric ergodicity and the spectral gap of non-reversible Markov chains
- Geometric ergodicity of Metropolis algorithms
- scientific article; zbMATH DE number 3121180 (Why is no real title available?)
- scientific article; zbMATH DE number 3688420 (Why is no real title available?)
- scientific article; zbMATH DE number 3519673 (Why is no real title available?)
- scientific article; zbMATH DE number 2079446 (Why is no real title available?)
- scientific article; zbMATH DE number 2208228 (Why is no real title available?)
- Inverse problems: a Bayesian perspective
- Large data and zero noise limits of graph-based semi-supervised learning algorithms
- Markov Chains
- Markov Chains and Stochastic Stability
- MCMC methods for functions: modifying old algorithms to make them faster
- Micro-local analysis for the Metropolis algorithm
- Minorization Conditions and Convergence Rates for Markov Chain Monte Carlo
- On the local Lipschitz stability of Bayesian inverse problems
- Optimal Transport
- Perturbation theory for Markov chains via Wasserstein distance
- Rates of convergence of the Hastings and Metropolis algorithms
- Refined generalizations of the triangle inequality on Banach spaces
- Sensitivity and convergence of uniformly ergodic Markov chains
- Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions
- Spectral theory and limit theorems for geometrically ergodic Markov processes
- Studying Convergence of Markov Chain Monte Carlo Algorithms Using Coupled Sample Paths
- Ten Lectures on Wavelets
- Two Metropolis--Hastings Algorithms for Posterior Measures with Non-Gaussian Priors in Infinite Dimensions
- Uncertainty Quantification and Weak Approximation of an Elliptic Inverse Problem
- Uncertainty quantification in graph-based classification of high dimensional data
- Weak convergence of measures
- Well-posed Bayesian inverse problems and heavy-tailed stable quasi-Banach space priors
- Well-posed Bayesian inverse problems with infinitely divisible and heavy-tailed prior measures
- Well-Posed Bayesian Inverse Problems: Priors with Exponential Tails
- What do we know about the Metropolis algorithm?
- Yet Another Look at Harris’ Ergodic Theorem for Markov Chains
Cited in
(6)- Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions
- Two Metropolis--Hastings Algorithms for Posterior Measures with Non-Gaussian Priors in Infinite Dimensions
- Almost sure convergence rates of adaptive increasingly rare Markov chain Monte Carlo
- Perturbation theory for killed Markov processes and quasi-stationary distributions
- Diffeomorphic measure matching with kernels for generative modeling
- Conditional optimal transport on function spaces
This page was built for publication: Spectral gaps and error estimates for infinite-dimensional Metropolis-Hastings with non-Gaussian priors
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6104013)
