Three-Toed Sloth

"Completely Random Measures for Bayesian Nonparametrics" (This Year at the DeGroot Lecture)

Attention conservation notice: Only of interest if you (1) care about specifying probability distributions on infinite-dimensional spaces for use in nonparametric Bayesian inference, and (2) are in Pittsburgh.

The CMU statistics department sponsors an annual distinguished lecture series in memory of our sainted founder, Morris H. DeGroot. This year, the lecturer is Michael Jordan. (I realize that's a common name; I mean the one my peers and I wanted to be when we grew up.)

"Completely Random Measures for Bayesian Nonparametrics"

Abstract: Bayesian nonparametric modeling and inference are based on using general stochastic processes as prior distributions. Despite the great generality of this definition, the great majority of the work in Bayesian nonparametrics is based on only two stochastic processes: the Gaussian process and the Dirichlet process. Motivated by the needs of applications, I present a broader approach to Bayesian nonparametrics in which priors are obtained from a class of stochastic processes known as "completely random measures" (Kingman, 1967). In particular I will present models based on the beta process and the Bernoulli process, and will discuss an application of these models to the analysis of motion capture data in computational vision.

(Joint work with Emily Fox, Erik Sudderth and Romain Thibaux.)

Time and place: 4:15 pm on Friday, 16 October 2009, in the Giant Eagle Auditorium in Baker Hall (room A51)

Update: I counted over 210 people in the audience.

Enigmas of Chance; Bayes, anti-Bayes