MWF 10:30-11:50AM in TTIC 530 (some of the classes will be canceled. Please see the schedule at the bottom of the page.)
Instructor: Nati Srebro.
TA: Behnam Neyshabur.
The purpose of this course is to gain a deeper understanding of machine learning by formalizing learning mathematically, studying both statistical and computational aspects of learning, and understanding how these two aspects are inseparable. The course is intended both for students interested in using machine learning methods and that would like to understand such methods better so as to use them more effectively, as well as for students interested in the mathematical aspects of learning or that intend on rigorously studying or developing learning algorithms.
We will discuss classic results and recent advances in statistical learning theory (mostly under the agnostic PAC model), touch on computational learning theory, and also explore the relationship with stochastic optimization and online regret analysis. Our emphasis will be on concept development and on obtaining a rigorous quantitative understanding of machine learning. We will also study techniques for analyzing and proving performance guarantees for learning methods.
|March 30th||What is Learning?*||PAC Learning and VC Theory I||No class|
|April 6th||PAC Learning and VC Theory II||MDL and PAC-Bayes||No class|
|April 13th||No class||Computational Complexity of Learning||Proper vs Improper Learning|
|April 20th||No class||Hardness of Improper Learning
|April 27th||No class||Real-Valued Loss||Scale-Sensitive Classes|
|May 4th||No class||SVMs, L1 Regularization||No class|
|May 11th||No class||L1 margin, Stability||Online Learning|
|May 18th||Online Gradient Descent||No class||Strong Convexity
Online Dual Averaging
|May 25th||No class||Mirror Descent
Online to Batch
|June 1st||Stochastic Optimization
Nearest Neighbor Classificaiton
|June 8th||Final Exam: Tuesday June 9, 10:30am|