Differential Evolution Markov Chain with snooker updater and fewer chains

Authors:
Cajo J. Ter Braak;Jasper A. Vrugt
Affiliations:
Biometris, Wageningen University and Research Centre, Wageningen, The Netherlands 6700 AC;Center for NonLinear Studies (CNLS), Los Alamos National Laboratory, Los Alamos, USA 87545
Venue:
Statistics and Computing
Year:
2008

Citing 7
Cited 2

Convergence of adaptive direction sampling

Journal of Multivariate Analysis
Differential Evolution – A Simple and Efficient Heuristic for Global Optimization over Continuous Spaces

Journal of Global Optimization
Markov Chain Monte Carlo Sampling using Direct Search Optimization

ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
Monte Carlo Statistical Methods (Springer Texts in Statistics)

Monte Carlo Statistical Methods (Springer Texts in Statistics)
Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series)

Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series)
A Markov Chain Monte Carlo version of the genetic algorithm Differential Evolution: easy Bayesian computing for real parameter spaces

Statistics and Computing
DRAM: Efficient adaptive MCMC

Statistics and Computing

Editorial: Special issue on adaptive Monte Carlo methods

Statistics and Computing
Using a Bayesian framework and global sensitivity analysis to identify strengths and weaknesses of two process-based models differing in representation of autotrophic respiration

Environmental Modelling & Software

Quantified Score

Hi-index	0.00

Visualization

Abstract

Differential Evolution Markov Chain (DE-MC) is an adaptive MCMC algorithm, in which multiple chains are run in parallel. Standard DE-MC requires at least N=2d chains to be run in parallel, where d is the dimensionality of the posterior. This paper extends DE-MC with a snooker updater and shows by simulation and real examples that DE-MC can work for d up to 50---100 with fewer parallel chains (e.g. N=3) by exploiting information from their past by generating jumps from differences of pairs of past states. This approach extends the practical applicability of DE-MC and is shown to be about 5---26 times more efficient than the optimal Normal random walk Metropolis sampler for the 97.5% point of a variable from a 25---50 dimensional Student t 3 distribution. In a nonlinear mixed effects model example the approach outperformed a block-updater geared to the specific features of the model.