Presented By: Department of Statistics
Statistics Department Seminar Series: Yves Atchade, Associate Professor, Department of Statistics, University of Michigan
“Regularization and computation with high-dimensional spike-and-slab posterior distributions”
Abstract:
This talk deals with Markov Chain Monte Carlo (MCMC) computation for high-dimensional Bayesian variable selection problems using spike-and-slab priors. We will introduce a regularized form of the posterior distribution that is more amenable to MCMC computation. In this setting we show that if a reasonably good frequentist variable screener is available, then the Bayesian variable selection problem can be solved with high probability in a time that is polynomial in the number of variables.
This talk deals with Markov Chain Monte Carlo (MCMC) computation for high-dimensional Bayesian variable selection problems using spike-and-slab priors. We will introduce a regularized form of the posterior distribution that is more amenable to MCMC computation. In this setting we show that if a reasonably good frequentist variable screener is available, then the Bayesian variable selection problem can be solved with high probability in a time that is polynomial in the number of variables.
Explore Similar Events
-
Loading Similar Events...
