Quantitative bounds of convergence for geometrically ergodic Markov chain in the Wasserstein distance with application to the Metropolis adjusted Langevin algorithm

DOI10.1007/s11222-014-9511-zzbMath1332.62282OpenAlexW2078038392MaRDI QIDQ5963544

Alain Durmus, Eric Moulines

Publication date: 22 February 2016

Published in: Statistics and Computing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11222-014-9511-z

zbMATH Keywords

Wasserstein distanceexplicit rate of convergenceMetropolis adjusted Langevin algorithm

Mathematics Subject Classification ID

Markov processes: estimation; hidden Markov models (62M05) Numerical analysis or methods applied to Markov chains (65C40) Markov processes (60Jxx)

Related Items (13)

Limit behavior of the invariant measure for Langevin dynamics ⋮ Dimension free convergence rates for Gibbs samplers for Bayesian linear mixed models ⋮ Quantitative contraction rates for Markov chains on general state spaces ⋮ Geometric convergence bounds for Markov chains in Wasserstein distance based on generalized drift and contraction conditions ⋮ Convergence of Position-Dependent MALA with Application to Conditional Simulation in GLMMs ⋮ Exact convergence analysis for metropolis–hastings independence samplers in Wasserstein distances ⋮ Perturbation theory for Markov chains via Wasserstein distance ⋮ On the convergence complexity of Gibbs samplers for a family of simple Bayesian random effects models ⋮ On the geometric ergodicity of Hamiltonian Monte Carlo ⋮ Convergence rate bounds for iterative random functions using one-shot coupling ⋮ Mixing rates for Hamiltonian Monte Carlo algorithms in finite and infinite dimensions ⋮ Stochastic Gradient MCMC for State Space Models ⋮ Wasserstein-based methods for convergence complexity analysis of MCMC with applications

Cites Work

• Unnamed Item
• Unnamed Item
• Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions
• Asymptotic coupling and a general form of Harris' theorem with applications to stochastic delay equations
• General state space Markov chains and MCMC algorithms
• Computable bounds for geometric convergence rates of Markov chains
• Exponential convergence of Langevin distributions and their discrete approximations
• Honest exploration of intractable probability distributions via Markov chain Monte Carlo.
• Bounds on regeneration times and convergence rates for Markov chains
• Statistical and computational inverse problems.
• Renewal theory and computable convergence rates for geometrically erdgodic Markov chains
• Error bounds for Metropolis-Hastings algorithms applied to perturbations of Gaussian measures in high dimensions
• Subgeometric rates of convergence of Markov processes in the Wasserstein metric
• Locally contracting iterated functions and stability of Markov chains
• Inverse problems: A Bayesian perspective
• MCMC METHODS FOR DIFFUSION BRIDGES
• Markov Chains and Stochastic Stability
• Time-reversible diffusions
• A numerical scheme for stochastic PDEs with Gevrey regularity
• Minorization Conditions and Convergence Rates for Markov Chain Monte Carlo
• MAP estimators and their consistency in Bayesian nonparametric inverse problems
• Optimal Transport
• MCMC methods for functions: modifying old algorithms to make them faster

This page was built for publication: Quantitative bounds of convergence for geometrically ergodic Markov chain in the Wasserstein distance with application to the Metropolis adjusted Langevin algorithm