Interacting multiple try algorithms with different proposal distributions

DOI10.1007/S11222-011-9301-9MaRDI QIDQ746262zbMATHOpenAlexWikidataFDO

Authors Roberto Casarin, Fabrizio Leisen, Radu V. Craiu

Publication date 16 October 2015

Published in Statistics and Computing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1011.1170

zbMATH Keywords

Markov chain Monte Carlosimulated annealingpopulation Monte Carlointeracting Monte Carlomultiple-try Metropolis

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Bayesian inference (62F15) Monte Carlo methods (65C05) Software, source code, etc. for problems pertaining to statistics (62-04)

Abstract: We propose a new class of interacting Markov chain Monte Carlo (MCMC) algorithms designed for increasing the efficiency of a modified multiple-try Metropolis (MTM) algorithm. The extension with respect to the existing MCMC literature is twofold. The sampler proposed extends the basic MTM algorithm by allowing different proposal distributions in the multiple-try generation step. We exploit the structure of the MTM algorithm with different proposal distributions to naturally introduce an interacting MTM mechanism (IMTM) that expands the class of population Monte Carlo methods. We show the validity of the algorithm and discuss the choice of the selection weights and of the different proposals. We provide numerical studies which show that the new algorithm can perform better than the basic MTM algorithm and that the interaction mechanism allows the IMTM to efficiently explore the state space.

Recommendations

• Interacting Hastings-Metropolis algorithms
• Parallel and interacting Markov chain Monte Carlo algorithm
• Scaling analysis of multiple-try MCMC methods
• Issues in the multiple try Metropolis mixing
• Convergence of adaptive and interacting Markov chain Monte Carlo algorithms

Cites work

• scientific article; zbMATH DE number 1085980 (Why is no real title available?)
• scientific article; zbMATH DE number 2106098 (Why is no real title available?)
• A Quantitative Study of Gene Regulation Involved in the Immune Response of Anopheline Mosquitoes
• A generalized multiple-try version of the reversible jump algorithm
• Annealing Markov Chain Monte Carlo with Applications to Ancestral Inference
• Finite mixture and Markov switching models.
• Improving Convergence of the Hastings–Metropolis Algorithm with an Adaptive Proposal
• Inference from iterative simulation using multiple sequences
• Iterated importance sampling in missing data problems
• Learn from thy neighbor: parallel-chain and regional adaptive MCMC
• Likelihood analysis of non-Gaussian measurement time series
• MODELING STOCHASTIC VOLATILITY: A REVIEW AND COMPARATIVE STUDY
• Markov chain Monte Carlo methods and the label switching problem in Bayesian mixture modeling
• Monte Carlo sampling methods using Markov chains and their applications
• Multiprocess parallel antithetic coupling for backward and forward Markov chain Monte Carlo
• Online data processing: comparison of Bayesian regularized particle filters
• Parallel and interacting Markov chain Monte Carlo algorithm
• Real-Parameter Evolutionary Monte Carlo With Applications to Bayesian Mixture Models
• Scaling analysis of multiple-try MCMC methods
• Sequential Monte Carlo Samplers
• The Multiple-Try Method and Local Optimization in Metropolis Sampling
• Towards optimal scaling of Metropolis-coupled Markov chain Monte Carlo

Cited in

(19)

• Adaptive Metropolis-Hastings sampling using reversible dependent mixture proposals
• On the empirical efficiency of local MCMC algorithms with pools of proposals
• A multiple-try Metropolis-Hastings algorithm with tailored proposals
• Efficient Gibbs sampling for Markov switching GARCH models
• Issues in the multiple try Metropolis mixing
• Parallel and interacting Markov chain Monte Carlo algorithm
• Improving the acceptance in Monte Carlo simulations: sampling through intermediate states
• An adaptive multiple-try Metropolis algorithm
• Generalized multiple-point Metropolis algorithms for approximate Bayesian computation
• Multiple-try simulated annealing algorithm for global optimization
• Adaptive Component-Wise Multiple-Try Metropolis Sampling
• A Stochastic Volatility Model With Realized Measures for Option Pricing
• On the flexibility of the design of multiple try Metropolis schemes
• Computing the halfspace depth with multiple try algorithm and simulated annealing algorithm
• Plateau proposal distributions for adaptive component-wise multiple-try metropolis
• Convergence rate of multiple-try Metropolis independent sampler
• A generalized multiple-try version of the reversible jump algorithm
• A multi-point Metropolis scheme with generic weight functions
• A parallel evolutionary multiple-try Metropolis Markov chain Monte Carlo algorithm for sampling spatial partitions

Describes a project that uses

Uses Software

• STRUCTURE

This page was built for publication: Interacting multiple try algorithms with different proposal distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q746262)