Bayesian Nonparametric Mixture Models

Add to your list(s) Download to your calendar using vCal

• Jurgen Van Gael, Engineering department, University of Cambridge
• Wednesday 28 October 2009, 16:30-18:00
• MR5, CMS.

If you have a question about this talk, please contact Richard Samworth.

Although Bayesian nonparametric models have been around for a while, recent advances in theory and computational methods have led to exciting new applications of this family of techniques. As a starting point into Bayesian nonparametrics, we will look at Bayesian nonparametric mixture models: why they are used and how they are used.

The Dirichlet process will be the basic building block for the mixture models which we discuss. We will discuss different – equivalent – representations of the Dirichlet process and explain how we can build a mixture model using them. We will touch on how to do inference in these models and show some example applications.

The discussion will not be going through one paper in particular but a very readable paper that touches on many issues which we will discuss is: Bayesian Density Estimation and Inference Using Mixtures, Michael D. Escobar, Mike West; Journal of the American Statistical Association, Vol. 90, 1995

This talk is part of the Statistics Reading Group series.

This talk is included in these lists:

• All CMS events
• All Talks (aka the CURE list)
• CMS Events
• DPMMS Lists
• DPMMS info aggregator
• DPMMS lists
• Hanchen DaDaDash
• Interested Talks
• MR5, CMS
• School of Physical Sciences
• Statistical Laboratory info aggregator
• Statistics Group
• Statistics Reading Group
• bld31

Note that ex-directory lists are not shown.