On the empirical efficiency of local MCMC algorithms with pools of proposals

DOI10.1002/cjs.11196zbMath1281.65002MaRDI QIDQ2870715

Matei Mireuta, Mylène Bédard

Publication date: 21 January 2014

Published in: Canadian Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1002/cjs.11196

zbMATH Keywords

numerical examples; regression; linear regression; Metropolis algorithm; Markov chain Monte Carlo methods; computational cost; correlated proposals; delayed rejection strategy; Bayesian logistic regressions; multiple-try algorithm

Mathematics Subject Classification ID

60J22: Computational methods in Markov chains

62J02: General nonlinear regression

65C05: Monte Carlo methods

65C40: Numerical analysis or methods applied to Markov chains

Related Items

Equation-solving estimator based on the general n-step MHDR algorithm, Conditional sequential Monte Carlo in high dimensions

Cites Work

• Unnamed Item
• Unnamed Item
• Diffusion limits of the random walk Metropolis algorithm in high dimensions
• On Bayesian model and variable selection using MCMC
• Interacting multiple try algorithms with different proposal distributions
• Scaling analysis of multiple-try MCMC methods
• Weak convergence and optimal scaling of random walk Metropolis algorithms
• Ordering and improving the performance of Monte Carlo Markov chains.
• Optimal scaling for various Metropolis-Hastings algorithms.
• On Metropolis-Hastings algorithms with delayed rejection
• A new strategy for speeding Markov chain Monte Carlo algorithms
• Scaling analysis of delayed rejection MCMC methods
• Delayed rejection in reversible jump Metropolis-Hastings
• Optimal scaling of Metropolis algorithms: Heading toward general target distributions
• The Multiple-Try Method and Local Optimization in Metropolis Sampling
• Applied Asymptotics
• Monte Carlo sampling methods using Markov chains and their applications
• An adaptive Metropolis algorithm