Error bounds for Metropolis-Hastings algorithms applied to perturbations of Gaussian measures in high dimensions
arXiv:1210.1180 · doi:10.1214/13-AAP926
Abstract
The Metropolis-adjusted Langevin algorithm (MALA) is a Metropolis-Hastings method for approximate sampling from continuous distributions. We derive upper bounds for the contraction rate in Kantorovich-Rubinstein-Wasserstein distance of the MALA chain with semi-implicit Euler proposals applied to log-concave probability measures that have a density w.r.t. a Gaussian reference measure. For sufficiently "regular" densities, the estimates are dimension-independent, and they hold for sufficiently small step sizes that do not depend on the dimension either. In the limit , the bounds approach the known optimal contraction rates for overdamped Langevin diffusions in a convex potential. A similar approach also applies to Metropolis-Hastings chains with Ornstein-Uhlenbeck proposals. In this case, the resulting estimates are still independent of the dimension but less optimal, reflecting the fact that MALA is a higher order approximation of the diffusion limit than Metropolis-Hastings with Ornstein-Uhlenbeck proposals.
Published in at http://dx.doi.org/10.1214/13-AAP926 the Annals of Applied Probability (http://www.imstat.org/aap/) by the Institute of Mathematical Statistics (http://www.imstat.org)
References in corpus (2)
Cited by in corpus (9)
- Statistical Aspects of Wasserstein Distances
- Reflection couplings and contraction rates for diffusions
- Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions
- On the Geometric Ergodicity of Hamiltonian Monte Carlo
- Coupling and Convergence for Hamiltonian Monte Carlo
- Convergence of unadjusted Hamiltonian Monte Carlo for mean-field models
- Two-scale coupling for preconditioned Hamiltonian Monte Carlo in infinite dimensions
- Mixing of Metropolis-Adjusted Markov Chains via Couplings: The High Acceptance Regime
- Scalable couplings for the random walk Metropolis algorithm