A stable manifold MCMC method for high dimensions

DOI10.1016/J.SPL.2014.03.016MaRDI QIDQ2453920zbMATH OpenOpenAlexFDO

Authors Alexandros Beskos

Publication date 11 June 2014

Published in Statistics \& Probability Letters (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1403.7711

zbMATH Keywords

infinite dimensionsCameron-Martin spacemetropolis-adjusted Langevin algorithmmanifold MCMC

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22)

Abstract: We combine two important recent advancements of MCMC algorithms: first, methods utilizing the intrinsic manifold structure of the parameter space; then, algorithms effective for targets in infinite-dimensions with the critical property that their mixing time is robust to mesh refinement.

Recommendations

• Fast Langevin based algorithm for MCMC in high dimensions
• Riemann manifold Langevin and Hamiltonian Monte Carlo methods. With discussion and authors' reply
• Dimension-independent likelihood-informed MCMC
• Efficient strategy for the Markov chain Monte Carlo in high-dimension with heavy-tailed target probability distribution
• Proximal Markov chain Monte Carlo algorithms

Cites work

• A note on Metropolis-Hastings kernels for general state spaces
• Advanced MCMC methods for sampling on diffusion pathspace
• Bayesian inference for partially observed stochastic differential equations driven by fractional Brownian motion
• Inverse problems: a Bayesian perspective
• MCMC METHODS FOR DIFFUSION BRIDGES
• MCMC methods for functions: modifying old algorithms to make them faster
• Optimal scaling for various Metropolis-Hastings algorithms.
• Posterior consistency of logistic Gaussian process priors in density estimation
• Riemann manifold Langevin and Hamiltonian Monte Carlo methods. With discussion and authors' reply
• Stochastic Equations in Infinite Dimensions

Cited in

(9)

• Scaling Up Bayesian Uncertainty Quantification for Inverse Problems Using Deep Neural Networks
• Bayesian spatiotemporal modeling for inverse problems
• Dimension-independent likelihood-informed MCMC
• Robust Inference of Manifold Density and Geometry by Doubly Stochastic Scaling
• Monte Carlo on manifolds in high dimensions
• MALA-within-Gibbs samplers for high-dimensional distributions with sparse conditional structure
• Data driven Dirichlet sampling on manifolds
• An Adaptive Independence Sampler MCMC Algorithm for Bayesian Inferences of Functions
• Adaptive dimension reduction to accelerate infinite-dimensional geometric Markov chain Monte Carlo

This page was built for publication: A stable manifold MCMC method for high dimensions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2453920)