Convergence rates of two-component MCMC samplers
Sign Up to like & getrecommendations! Published in 2022 at "Bernoulli"
DOI: 10.3150/21-bej1369
Abstract: Component-wise MCMC algorithms, including Gibbs and conditional Metropolis-Hastings samplers, are commonly used for sampling from multivariate probability distributions. A long-standing question regarding Gibbs algorithms is whether a deterministic-scan (systematic-scan) sampler converges faster than its random-scan… read more here.
Keywords: metropolis hastings; conditional metropolis; convergence rates; two component ... See more keywords