ECE 543: Statistical Learning Theory (Spring 2018)

Instructor
Maxim Raginsky (maxim at illinois dot edu)
Teaching Assistants:
  • Georgios Rovatsos (rovatso2 at illinois edu)
  • Surya Sankagiri (ss19 at illinois dot edu)
Administrivia
About this course
Regular weekly schedule
Coursework
Academic integrity policies

Announcements

April 17
April 12
March 29
March 1
February 8
January 25
January 16

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.
Materials
Required readings will be drawn from:
Coursework
Grades will be based regular written homeworks (50% total), one ninety-minute exam (20%), and a project (30%).

Regular weekly schedule

Lectures
Tue Thu 2:00-3:20 pm, 2015 ECE Building
Office hours:
instructor Wednesdays 1:00-2:00pm, 162 CSL
TAs Mondays 2:30-3:30pm, 114 CSL (Surya)
Tuesdays 5:00-6:00pm, 114 CSL (George)
Homework
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.