Syllabus

Course Meeting Times

Lectures: 2 sessions / week, 1.5 hours / session

Prerequisites

18.100C Real Analysis

18.06SC Linear Algebra

18.05 Introduction to Probability and Statistics

Description

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:

  1. The Statistical Theory of Machine Learning.
    1. Classification, Regression, Aggregation
    2. Empirical Risk Minimization, Regularization
    3. Suprema of Empirical Processes
  2. Algorithms and Convexity.
    1. Boosting
    2. Kernel Methods
    3. Convex Optimization
  3. Online Learning.
    1. Online Convex Optimization
    2. Partial Information: Bandit Problems
    3. Blackwell's Approachability

Grading

ACTIVITIES PERCENTAGES
Assignments 40%
Final Project 50%
Lecture Notes Scribing 10%
  1. Homework 40%

    There are 3 homework assignments.

  2. 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).

  3. Lecture notes scribing 10%