Fast Langevin based algorithm for MCMC in high dimensions

DOI10.1214/16-AAP1257zbMath1373.60053arXiv1507.02166OpenAlexW2953328789MaRDI QIDQ1676438

Konstantinos C. Zygalakis, Gareth O. Roberts, Alain Durmus, Gilles Vilmart

Publication date: 7 November 2017

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

Full work available at URL: https://arxiv.org/abs/1507.02166

zbMATH Keywords

weak convergenceMarkov chain Monte Carloexponential ergodicitydiffusion limit

Mathematics Subject Classification ID

Central limit and other weak theorems (60F05) Monte Carlo methods (65C05)

Related Items (10)

A Micro-Macro Markov Chain Monte Carlo Method for Molecular Dynamics using Reaction Coordinate Proposals ⋮ Nonasymptotic bounds for sampling algorithms without log-concavity ⋮ Dynamic network data envelopment analysis with a sequential structure and behavioural-causal analysis: application to the Chinese banking industry ⋮ Multi-index antithetic stochastic gradient algorithm ⋮ Bayesian Stochastic Gradient Descent for Stochastic Optimization with Streaming Input Data ⋮ Informed Proposals for Local MCMC in Discrete Spaces ⋮ Improving dynamical properties of metropolized discretizations of overdamped Langevin dynamics ⋮ Asymptotic variance for random walk Metropolis chains in high dimensions: logarithmic growth via the Poisson equation ⋮ Random walk Metropolis algorithm in high dimension with non-Gaussian target distributions ⋮ Maximum Entropy Methods for Texture Synthesis: Theory and Practice

This page was built for publication: Fast Langevin based algorithm for MCMC in high dimensions