Error bounds for Metropolis-Hastings algorithms applied to perturbations of Gaussian measures in high dimensions

DOI10.1214/13-AAP926zbMath1296.60195arXiv1210.1180MaRDI QIDQ2443195

Andreas Eberle

Publication date: 4 April 2014

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

Full work available at URL: https://arxiv.org/abs/1210.1180

zbMATH Keywords

Markov chain Monte CarlocouplingMetropolis algorithmEuler schemeLangevin diffusioncontractivity of Markov kernels

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Monte Carlo methods (65C05) Discrete-time Markov processes on general state spaces (60J05) Numerical analysis or methods applied to Markov chains (65C40)

Related Items (19)

Continuum limit and preconditioned Langevin sampling of the path integral molecular dynamics ⋮ Quantitative contraction rates for Markov chains on general state spaces ⋮ Unnamed Item ⋮ Reflection couplings and contraction rates for diffusions ⋮ Unnamed Item ⋮ Coupling and convergence for Hamiltonian Monte Carlo ⋮ Complexity results for MCMC derived from quantitative bounds ⋮ On the accept-reject mechanism for Metropolis-Hastings algorithms ⋮ Convergence of unadjusted Hamiltonian Monte Carlo for mean-field models ⋮ Exact convergence analysis for metropolis–hastings independence samplers in Wasserstein distances ⋮ A Bayesian Approach to Estimating Background Flows from a Passive Scalar ⋮ Perturbation theory for Markov chains via Wasserstein distance ⋮ Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions ⋮ Approximate Spectral Gaps for Markov Chain Mixing Times in High Dimensions ⋮ Efficient strategy for the Markov chain Monte Carlo in high-dimension with heavy-tailed target probability distribution ⋮ Empirical optimal transport on countable metric spaces: distributional limits and statistical applications ⋮ Quantitative bounds of convergence for geometrically ergodic Markov chain in the Wasserstein distance with application to the Metropolis adjusted Langevin algorithm ⋮ Two-scale coupling for preconditioned Hamiltonian Monte Carlo in infinite dimensions ⋮ On the geometric ergodicity of Hamiltonian Monte Carlo

Cites Work

• Diffusion limits of the random walk Metropolis algorithm in high dimensions
• Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions
• Reflection coupling and Wasserstein contractivity without convexity
• Markov chains and stochastic stability
• Coupling methods for multidimensional diffusion processes
• Exponential convergence of Langevin distributions and their discrete approximations
• Weak convergence and optimal scaling of random walk Metropolis algorithms
• Optimal scaling and diffusion limits for the Langevin algorithm in high dimensions
• Rate of convergence for ergodic continuous Markov processes: Lyapunov versus Poincaré
• Simulated annealing in convex bodies and an \(O^{*}(n^{4}\)) volume algorithm
• Transport inequalities, gradient estimates, entropy and Ricci curvature
• The geometry of logconcave functions and sampling algorithms
• MCMC METHODS FOR DIFFUSION BRIDGES
• Pathwise accuracy and ergodicity of metropolized integrators for SDEs
• Optimal Scaling of Discrete Approximations to Langevin Diffusions
• A random polynomial-time algorithm for approximating the volume of convex bodies
• Random walks and anO*(n5) volume algorithm for convex bodies
• Ergodicity for Infinite Dimensional Systems
• Hit-and-Run from a Corner
• Monte Carlo sampling methods using Markov chains and their applications
• Optimal Transport
• MCMC methods for functions: modifying old algorithms to make them faster
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Error bounds for Metropolis-Hastings algorithms applied to perturbations of Gaussian measures in high dimensions