CS 281B / Stat 241B, Spring 2006:

Statistical Learning Theory


Office hours
Instructor Peter Bartlett bartlett at cs Tu 5:00-6:00, Evans 399. Thu 11:00-12:00, Soda 527.
Ambuj Tewari
ambuj at cs Soda 551. Tu 4:00-5:00, Fr 11:00-12:00

Lectures:  Soda 405. Tuesday/Thursday 9:30-11:00.

Course description

This course will provide an introduction to the analysis of advanced statistical and computational methods for the modeling of complex, multivariate data. It will concentrate on the development of theoretical concepts to support such methods, and in particular the analysis of the statistical properties of prediction methods.
Prerequisites: CS281A/Stat241A, or advanced training in probability or statistics, at the level of Stat 205A or Stat 210A.
[More details]


There will be regular homework assignments, due at the class three lectures after being passed out. Late homeworks will not be accepted.

You will be expected to act as scribe for a small number of lectures, preparing a latex version of lecture notes that will be posted on the web site. (Latex template)

In addition, you will present one paper during one of the lectures. Please sign up for papers on this list, by email to ambuj at cs.

There will be a final project in an area relevant to the course. Feel free to discuss topics with me, or ask for suggestions.
Project proposals are due April 4 (one or two paragraphs in an email message to bartlett at cs).
Project reports are due May 9. We will have project poster presentations on May 9 and May 11, 9:30-11:00 in Soda 405.




Lecture notes