Reversible Jump PDMP Samplers for Variable Selection
Authors:
- Matthew SuttonMSMatthew Sutton
Preprint
Abstract
A new class of Markov chain Monte Carlo (MCMC) algorithms, based on simulating piecewise deterministic Markov processes (PDMPs), have recently shown great promise: they are non-reversible, can mix better than standard MCMC algorithms, and can use subsampling ideas to speed up computation in big data scenarios. However, current PDMP samplers can only sample from posterior densities that are differentiable almost everywhere, which precludes their use for model choice. Motivated by variable selection problems, we show how to develop reversible jump PDMP samplers that can jointly explore the discrete space of models and the continuous space of parameters. Our framework is general: it takes any existing PDMP sampler, and adds two types of trans-dimensional moves that allow for the addition or removal of a variable from the model. We show how the rates of these trans-dimensional moves can be calculated so that the sampler has the correct invariant distribution. Simulations show that the new samplers can mix better than standard MCMC algorithms. Our empirical results show they are also more efficient than gradient-based samplers that avoid model choice through use of continuous spike-and-slab priors which replace a point mass at zero for each parameter with a density concentrated around zero.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- Extended stochastic gradient Markov chain Monte Carlo for large-scale Bayesian variable selectionBiometrika, 2020
- Forward Event-Chain Monte Carlo: Fast Sampling by Randomness Control in Irreversible Markov ChainsJournal of Computational and Graphical Statistics, 2020
- Coordinate sampler: a non-reversible Gibbs-like MCMC samplerStatistics and Computing, 2019
- Piecewise deterministic Markov processes for scalable Monte Carlo on restricted domainsStatistics & Probability Letters, 2018
- The Bouncy Particle Sampler: A Nonreversible Rejection-Free Markov Chain Monte Carlo MethodJournal of the American Statistical Association, 2018
- Programming With Models: Writing Statistical Algorithms for General Model Structures With NIMBLEJournal of Computational and Graphical Statistics, 2017
- Generalized event-chain Monte Carlo: Constructing rejection-free global-balance algorithms from infinitesimal stepsThe Journal of Chemical Physics, 2014
- The horseshoe estimator for sparse signalsBiometrika, 2010
- Nonparametric regression using Bayesian variable selectionJournal of Econometrics, 1996
- Variable Selection and Model Comparison in Regression1996