Adaptive Component-Wise Multiple-Try Metropolis Sampling
- 5 November 2018
- journal article
- research article
- Published by Taylor & Francis in Journal of Computational and Graphical Statistics
- Vol. 28 (2) , 276-289
Abstract
One of the most widely used samplers in practice is the component-wise Metropolis-Hastings (CMH) sampler that updates in turn the components of a vector valued Markov chain using accept-reject moves generated from a proposal distribution. When the target distribution of a Markov chain is irregularly shaped, a ‘good’ proposal distribution for one region of the state space might be a ‘poor’ one for another region. We consider a component-wise multiple-try Metropolis (CMTM) algorithm that chooses from a set of candidate moves sampled from different distributions. The computational efficiency is increased using an adaptation rule for the CMTM algorithm that dynamically builds a better set of proposal distributions as the Markov chain runs. The ergodicity of the adaptive chain is demonstrated theoretically. The performance is studied via simulations and real data examples.Keywords
All Related Versions
This publication has 28 references indexed in Scilit:
- Learn From Thy Neighbor: Parallel-Chain and Regional Adaptive MCMCJournal of the American Statistical Association, 2009
- Examples of Adaptive MCMCJournal of Computational and Graphical Statistics, 2009
- BGX: a Bioconductor package for the Bayesian integrated analysis of Affymetrix GeneChipsBMC Bioinformatics, 2007
- Coupling and Ergodicity of Adaptive Markov Chain Monte Carlo AlgorithmsJournal of Applied Probability, 2007
- On the ergodicity properties of some adaptive MCMC algorithmsThe Annals of Applied Probability, 2006
- On adaptive Markov chain Monte Carlo algorithmsBernoulli, 2005
- General state space Markov chains and MCMC algorithmsProbability Surveys, 2004
- An Adaptive Metropolis AlgorithmBernoulli, 2001
- The Multiple-Try Method and Local Optimization in Metropolis SamplingJournal of the American Statistical Association, 2000
- Practical Markov Chain Monte CarloStatistical Science, 1992