Mixing of Metropolis-adjusted Markov chains via couplings: the high acceptance regime

DOI10.1214/24-EJP1150MaRDI QIDQ6595705FDOQ6595705

Authors: Nawaf Bou-Rabee, Stefan Oberdörster 

Publication date: 30 August 2024

Published in: Electronic Journal of Probability (Search for Journal in Brave)

Recommendations

• Metropolis-Hastings transition kernel couplings
• Fast mixing of Metropolized Hamiltonian Monte Carlo: benefits of multi-step gradients
• Log-concave sampling: Metropolis-Hastings algorithms are fast
• Explicit convergence bounds for Metropolis Markov chains: isoperimetry, spectral gaps and profiles
• Approximate spectral gaps for Markov chain mixing times in high dimensions

zbMATH Keywords

Metropolis-Hastingsmixing timecouplingsnon-reversible Markov chainhigh acceptance regime

Mathematics Subject Classification ID

Diffusion processes (60J60) Discrete-time Markov processes on general state spaces (60J05) Continuous-time Markov processes on general state spaces (60J25)

Cites Work

• Markov chains and mixing times. With a chapter on ``Coupling from the past by James G. Propp and David B. Wilson.
• Exponential convergence of Langevin distributions and their discrete approximations
• Analysis of a nonreversible Markov chain sampler.
• Monte Carlo sampling methods using Markov chains and their applications
• A note on Metropolis-Hastings kernels for general state spaces
• Geometric convergence and central limit theorems for multidimensional Hastings and Metropolis algorithms
• Equation of state calculations by fast computing machines
• Markov chains and stochastic stability
• General state space Markov chains and MCMC algorithms
• Rates of convergence of the Hastings and Metropolis algorithms
• Randomized Hamiltonian Monte Carlo as scaling limit of the bouncy particle sampler and dimension-free convergence rates
• Minorization Conditions and Convergence Rates for Markov Chain Monte Carlo
• The Markov chain Monte Carlo revolution
• The Andersen thermostat in molecular dynamics
• Computable bounds for geometric convergence rates of Markov chains
• Yet Another Look at Harris’ Ergodic Theorem for Markov Chains
• Title not available (Why is that?)
• Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions
• Ergodicity for SDEs and approximations: locally Lipschitz vector fields and degenerate noise.
• Free energy computations. A mathematical perspective
• Hybrid Monte Carlo on Hilbert spaces
• Error bounds for Metropolis-Hastings algorithms applied to perturbations of Gaussian measures in high dimensions
• Nonasymptotic mixing of the MALA algorithm
• Asymptotic coupling and a general form of Harris' theorem with applications to stochastic delay equations
• Geometric Numerical Integration
• Markov Chains
• Pathwise accuracy and ergodicity of metropolized integrators for SDEs
• High-dimensional Bayesian inference via the unadjusted Langevin algorithm
• A geometric interpretation of the Metropolis-Hastings algorithm.
• Subgeometric rates of convergence of Markov processes in the Wasserstein metric
• Subgeometric rates of convergence in Wasserstein distance for Markov chains
• Quantitative bounds for Markov chain convergence: Wasserstein and total variation distances
• One-shot coupling for certain stochastic recursive sequences.
• Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
• Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
• Two-scale coupling for preconditioned Hamiltonian Monte Carlo in infinite dimensions
• Lectures on convex optimization
• Couplings and quantitative contraction rates for Langevin dynamics
• Unbiased Markov Chain Monte Carlo Methods with Couplings
• Title not available (Why is that?)
• On sampling from a log-concave density using kinetic Langevin diffusions
• On explicit \(L^2\)-convergence rate estimate for underdamped Langevin dynamics
• On the geometric ergodicity of Hamiltonian Monte Carlo
• Quantitative contraction rates for Markov chains on general state spaces
• Quantitative Harris-type theorems for diffusions and McKean-Vlasov processes
• Irreducibility and geometric ergodicity of Hamiltonian Monte Carlo
• Coupling and convergence for Hamiltonian Monte Carlo
• Estimates of the determinant of a perturbed identity matrix
• Complexity results for MCMC derived from quantitative bounds
• Geometric integrators and the Hamiltonian Monte Carlo method
• Unbiased Hamiltonian Monte Carlo with couplings
• Convergence of unadjusted Hamiltonian Monte Carlo for mean-field models
• Mixing time guarantees for unadjusted Hamiltonian Monte Carlo
• High-dimensional MCMC with a standard splitting scheme for the underdamped Langevin diffusion
• Fast mixing of Metropolized Hamiltonian Monte Carlo: benefits of multi-step gradients
• Couplings for Andersen dynamics
• Connecting the Dots: Numerical Randomized Hamiltonian Monte Carlo with State-Dependent Event Rates

Cited In (2)

• Metropolis-Hastings transition kernel couplings
• Tuning diagonal scale matrices for HMC

This page was built for publication: Mixing of Metropolis-adjusted Markov chains via couplings: the high acceptance regime

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6595705)