Abstract
We establish -exponential convergence rate for three popular piecewise deterministic Markov processes for sampling: the randomized Hamiltonian Monte Carlo method, the zigzag process and the bouncy particle sampler. Our analysis is based on a variational framework for hypocoercivity, which combines a Poincaré-type inequality in time-augmented state space and a standard energy estimate. Our analysis provides explicit convergence rate estimates, which are more quantitative than existing results.
Funding Statement
This work is supported in part by National Science Foundation via grants CCF-1910571 and DMS-2012286.
Citation
Jianfeng Lu. Lihan Wang. "On explicit -convergence rate estimate for piecewise deterministic Markov processes in MCMC algorithms." Ann. Appl. Probab. 32 (2) 1333 - 1361, April 2022. https://doi.org/10.1214/21-AAP1710
Information