Sampling latent Gaussian models and hierarchical modelling

Speaker: Iain Murray (University of Edinburgh)

Time: 3:00PM
Date: Thu 7th April 2011

Location: Statistics Seminar Room- L550 Library building

Abstract
Sometimes hyperparameters of hierarchical probabilistic models are not well-specified enough to be optimized. In some scientific applications inferring their posterior distribution is the objective of learning. Using a simple example, I explain why Markov chain Monte Carlo (MCMC) simulation can be difficult, and offer a solution for latent Gaussian models.

(This talk is part of the Statistics and Actuarial Science series.)