Instructors:

Professor Marina Meila

E-mail: mmp@stat.washington.edu

Office: B321 Padelford

Phone : 543-8484

Professor Thomas Richardson

E-mail: tsr@stat.washington.edu

Office: B303 Padelford

Professor Jeff Bilmes, Electrical Engineering

Time/Place: (First meeting)

Thursday January 10th at 5pm in Padelford C-301

Description:
A typical problem in statistical inference and machine learning is to find, among a class of probability distributions, the one that optimizes a certain criterion. For example, to find the model that best fits the data by maximizing the likelihood. Or, inferring the values of some unobserved variables from other, observed, variables, like in medical diagnosis.

Convex analysis provides a geometric insight to this type of problems. With it comes a very powerful mathematical apparatus, that can readily be applied to the above problems, by realizing that many families of distributions are convex sets and many optimality criteria are convex functions.

We will meet for two hours every week. The format will be that of a reading group: each time two participants prepare and lead the discussion of a paper or a book chapter. Credit will be given for participation.The first meeting will take place on Thursday January 10 at 5pm in Padelford C-301. At that meeting we will decide the time and place for the rest of the course; we envisage it taking place in the late afternoon (i.e after 4:30). If you cannot attend the first meeting but would like to participate, send mail (before January 10) to one of the instructors with the times and days that would suit you.