ECE 543: Statistical Learning Theory (Spring 2021)

Maxim Raginsky (maxim at illinois dot edu)
Teaching Assistant
Tanya Veeravalli (veerava2 at illinois dot edu)

About this course
Regular weekly schedule
Academic integrity policies


April 15
March 25
March 5
March 4
February 15
February 12
February 11
February 3
January 28
January 26
January 15

About this course

What is this?
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.
Required readings will be drawn from: Another indispensable resource is Matus Telgarsky's set of lectures on deep learning theory.
Grades will be based on regular written homeworks (70% total) and a project (30%).

Regular weekly schedule

Tue Thu 2:00-3:20 pm, via Zoom (link posted on Piazza)
Office hours:
instructor Thu, 11:00 am - noon via Zoom (link posted on Piazza)
TAs Mon, 4:00 - 5:00 pm via Zoom (link posted on Piazza)
Due Thursdays, by the end of the day, uploaded to Compass (submission instructions).
Homeworks are released at least one week before the due date.
Under normal circumstances, graded homework should be returned within 10 days of submission.