In search of lost mixing time: adaptive Markov chain Monte Carlo schemes for Bayesian variable selection with very largep
Authors:
Open Access
- 5 October 2020
- journal article
- research article
- Published by Oxford University Press (OUP) in Biometrika
- Vol. 108 (1) , 53-69
Abstract
Summary: The availability of datasets with large numbers of variables is rapidly increasing. The effective application of Bayesian variable selection methods for regression with these datasets has proved difficult since available Markov chain Monte Carlo methods do not perform well in typical problem sizes of interest. We propose new adaptive Markov chain Monte Carlo algorithms to address this shortcoming. The adaptive design of these algorithms exploits the observation that in large-$p$, small-$n$ settings, the majority of the $p$ variables will be approximately uncorrelated a posteriori. The algorithms adaptively build suitable nonlocal proposals that result in moves with squared jumping distance significantly larger than standard methods. Their performance is studied empirically in high-dimensional problems and speed-ups of up to four orders of magnitude are observed.
Keywords
This publication has 42 references indexed in Scilit:
- Optimal scaling of random walk Metropolis algorithms with discontinuous target densitiesThe Annals of Applied Probability, 2012
- Rao–Blackwellization for Bayesian Variable Selection and Model Averaging in Linear and Binary Regression: A Novel Data Augmentation ApproachJournal of the American Statistical Association, 2011
- Bayesian Adaptive Sampling for Variable Selection and Model AveragingJournal of Computational and Graphical Statistics, 2011
- 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
- Adaptive sampling for Bayesian variable selectionBiometrika, 2005
- The Practical Implementation of Bayesian Model Selection2001
- Optimal metropolis algorithms for product measures on the vertices of a hypercubeStochastics and Stochastic Reports, 1998
- Weak convergence and optimal scaling of random walk Metropolis algorithmsThe Annals of Applied Probability, 1997
- Optimum Monte-Carlo sampling using Markov chainsBiometrika, 1973