A Mixture-Based Approach to Regional Adaptation for MCMC

Abstract

Recent advances in adaptive Markov chain Monte Carlo (AMCMC) include the need for regional adaptation in situations when the optimal transition kernel is different across different regions of the sample space. Motivated by these findings, we propose a mixture-based approach to determine the partition needed for regional AMCMC. The mixture model is fitted using an online EM algorithm (see Andrieu and Moulines, 2006) which allows us to bypass simultaneously the heavy computational load and to implement the regional adaptive algorithm with online recursion (RAPTOR). The method is tried on simulated as well as real data examples.

References in corpus (5)

• Online EM Algorithm for Latent Data Models
• On the ergodicity properties of some adaptive MCMC algorithms
• Equi-energy sampler with applications in statistical inference and statistical mechanics
• Annealed Importance Sampling
• Small-world MCMC and convergence to multi-modal distributions: From slow mixing to fast mixing

Cited by in corpus (4)

• Adaptive Gibbs samplers and related MCMC methods
• Stability of adversarial Markov chains, with an application to adaptive MCMC algorithms
• Relabeling and Summarizing Posterior Distributions in Signal Decomposition Problems when the Number of Components is Unknown
• Summarizing posterior distributions in signal decomposition problems when the number of components is unknown