Instruction will be online starting on March 23. If you are registered for the class, you will receive an email with instructions on how to access the online material. If you are not registered, please send an email to rsrikant@illinois.edu and I will add you to course email list.

Term: Spring 2020

Prerequisites: ECE 534 (Random Processes)

Instructor: Prof. R. Srikant, rsrikant@illinois.edu

TAs: Liming Wang (lwang114@illinois.edu) and Kaiqing Zhang (kzhang66@illinois.edu)

Prof. Srikant’s Office Hours: 5-6 Thursdays 107 CSL.

TAs' Office Hours: Liming Wang (11 am-noon Mondays, Room: 3036 ECEB), Kaiqing Zhang (4-5 pm Fridays, Room: 2036 ECE)

Lectures: 5-8 pm Mondays, 2015 ECEB

Spring Break: March 14-22

Last Day of instruction: May 6

Link to Spring 2019 and previous versions of the course

Outline (Time Permitting):

• Empirical Risk Minimization and Generalization Bounds via Rademacher Complexity and VC Dimension
• Applications to SVM, Kernel Methods, Neural Networks, AdaBoost, Regression, Online Learning, Multiclass Classification
• Other topics: Stability and Generalization, Dimensionality Reduction, Minimax Lower Bounds

Grading (Link to compass):

• Homework (80%): Collaboration is allowed, but solutions have to be written individually. Directly copying solutions will be viewed very unfavorably. Homework is due in class on the dates mentioned in the problem sets. Late homework will not be accepted.
• Final exam (20%): Due: 11 am, Friday May 8. Additional Instructions by email

References:

• B. Hajek and M. Raginsky. Statistical Learning Theory.
• S. Shalev-Shwartz and S. Ben David, Understanding Machine Learning: From Theory to Algorithms.
• M. Mohri, A. Rostamizadeh, and A. Talwalkar. Foundations of Machine Learning