ECE 543: Statistical Learning Theory (Spring 2018)
- Important dates
- Midterm 1: Mon Mar 12, 7-9:30pm, 2017 ECEB
Midterm 2: Mon Apr 23, 7-9:30pm, 2017 ECEB
Project presentations: TBA
- January 16
Welcome! Watch this space for all important course-related announcements.
- The first lecture is this Tuesday, January 16.
- The first homework will be assigned on Thursday, January 25, due next Thursday, February 1. Each student must submit their own individual solutions on Compass2g, details to be announced soon.
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:
- Grades will be based on regular written homeworks (40% total), two ninety-minute exams (20% each), and a project (20%).
Regular weekly schedule
- Tue Thu 2:00-3:20 pm, 2015 ECE Building
| instructor || day/time TBA, 162 CSL
| TAs || TBA
- Due Thursdays, by the end of the day, uploaded to Compass (details to follow soon).
Homeworks are released at least one week before the due date.
Under normal circumstances, graded homework should be returned within 10 days of submission.