Mixing of Metropolis-Adjusted Markov Chains via Couplings: The High Acceptance Regime
arXiv:2308.04634 · doi:10.1214/24-EJP1150
Abstract
We present a coupling framework to upper bound the total variation mixing time of various Metropolis-adjusted, gradient-based Markov kernels in the `high acceptance regime'. The approach uses a localization argument to boost local mixing of the underlying unadjusted kernel to mixing of the adjusted kernel when the acceptance rate is suitably high. As an application, mixing time guarantees are developed for a non-reversible, adjusted Markov chain based on the kinetic Langevin diffusion, where little is currently understood.
arXiv comment33 pages
References in corpus (14)
- Canonical sampling through velocity-rescaling
- General state space Markov chains and MCMC algorithms
- Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions
- Geometric integrators and the Hamiltonian Monte Carlo method
- Subgeometric rates of convergence of Markov processes in the Wasserstein metric
- Coupling and Convergence for Hamiltonian Monte Carlo
- Quantitative bounds for Markov chain convergence: Wasserstein and total variation distances
- Pathwise Accuracy and Ergodicity of Metropolized Integrators for SDEs
- An efficient sampling algorithm for Variational Monte Carlo
- Error bounds for Metropolis-Hastings algorithms applied to perturbations of Gaussian measures in high dimensions
- Mixing Time Guarantees for Unadjusted Hamiltonian Monte Carlo
- Convergence of unadjusted Hamiltonian Monte Carlo for mean-field models
- Couplings for Andersen Dynamics
- Two-scale coupling for preconditioned Hamiltonian Monte Carlo in infinite dimensions