# ECE 598MR: Statistical Learning Theory (Fall 2013)

##
Maxim Raginsky

TTh 9:30-10:50am, 106B3 Engineering Hall

### Announcements

- There will be office hours on Monday, December 2, from 9 am to 11:30 am in 162 CSL.
- Due date for Homework 3 is extended to Tuesday, December 3.
- On Tuesday, November 5, there will be a guest lecture by Prof. Sewoong Oh (IESE) on matrix completion; there will be no class on Thursday, November 7.
- There will be no office hours on Thursday, October 31.
- There is a correction to Homework 2, Problem 1.
- There will be no class on Thursday, October 3, due to the Allerton Conference.
- There will be no office hours on September 19; there will be extra office hours on Tuesday, September 24 in addition to the usual Thursday office hours.
- There is a correction to Homework 1, Problem 4, part (a).
- Due date for Homework 1 is extended to Friday, September 27.
- Homework 1 is out.
- There will be no class and no office hours on Thursday, September 12.
- Office hours are 2 pm to 4 pm on Thursdays in 162 CSL.

### About this class

Statistical learning theory is a burgeoning research field at the intersection of probability, statistics, computer science, and optimization that studies the performance of computer algorithms for making predictions on the basis of training data.
The following topics will be covered: basics of statistical decision theory; concentration inequalities; supervised and unsupervised learning; empirical risk minimization; complexity-regularized estimation; generalization bounds for learning algorithms; VC dimension and Rademacher complexities; minimax lower bounds; online learning and optimization. Along with the general theory, we will discuss a number of applications of statistical learning theory to signal processing, information theory, and adaptive control.

Basic prerequisites include probability theory and random processes, calculus, and linear algebra. Other necessary material and background will be introduced as needed.

### Other statistical learning theory classes

The rough outline of the course is fairly standard, although the precise selection of topics will reflect my own interests and expertise. Here is a link to a similar course I had taught at Duke University:
Here is a sampling of similar courses at other institutions: