Homework 4 is posted, due by the end of the day on Tuesday, April 27.
Recordings of all lectures up to April 15 are now available.
March 25
Homework 3 is posted, due by the end of the day on Tuesday, April 6.
Recordings of all lectures up to March 23 are now available.
March 5
There was a typo in Problem 1 of Homework 2. Revised version is posted.
March 4
In-class notes and video recordings of Lectures 7-12 are now available.
Homework 2 is posted, due by the end of the day on Tuesday, March 16.
February 15
There will be TA office hours this week on Tuesday, February 16, 9:00-10:00 am.
Starting next week, TA office hours will be on Mondays, 4:00-5:00 pm.
February 12
Since Wednesday, February 17, is a no-instruction day, there will be no TA office hours that week. Homework 1 is now due by the end of Wednesday, February 24.
February 11
In-class notes and video recording of Lectures 4-6 are now available.
Information about homework submissions and final project is available on the coursework page.
Homework 1 is posted, due by the end of the day on Thursday, February 18.
February 3
In-class notes and video recording of Lectures 2 and 3 are now available.
January 28
In-class notes and video recording of Lecture 1 are now available.
January 26
Zoom link and passcode for the course are posted on Piazza.
Welcome! Watch this space for all important course-related announcements.
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.
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.