Course Meeting Times
Lectures: 2 sessions / week, 1.5 hours / session
Broadly speaking, Machine Learning refers to the automated identification of patterns in data. As such it has been a fertile ground for new statistical and algorithmic developments. The purpose of this course is to provide a mathematically rigorous introduction to these developments with emphasis on methods and their analysis.
The Topics Covered
The class will be split in three main parts:
- The Statistical Theory of Machine Learning.
- Classification, Regression, Aggregation
- Empirical Risk Minimization, Regularization
- Suprema of Empirical Processes
- Algorithms and Convexity.
- Kernel Methods
- Convex Optimization
- Online Learning.
- Online Convex Optimization
- Partial Information: Bandit Problems
- Blackwell's Approachability
|Lecture Notes Scribing||10%|
- Homework 40%
There are 3 homework assignments.
- Final project 50%
The final project should be in any area related to one of the topics of the course or use tools that are developed in class. Examples include: implementing an algorithm for real data, extend an existing method or prove a theoretical result (or a combination of these). You will need to submit a written report (~10 pages) and give a presentation in class in the last week of semester (the duration will depend on the size of the class).
- Lecture notes scribing 10%