18.409 | Spring 2015 | Graduate

Algorithmic Aspects of Machine Learning

Course Description

This course is organized around algorithmic issues that arise in machine learning. Modern machine learning systems are often built on top of algorithms that do not have provable guarantees, and it is the subject of debate when and why they work. In this class, we focus on designing algorithms whose performance we can …
This course is organized around algorithmic issues that arise in machine learning. Modern machine learning systems are often built on top of algorithms that do not have provable guarantees, and it is the subject of debate when and why they work. In this class, we focus on designing algorithms whose performance we can rigorously analyze for fundamental machine learning problems.
Learning Resource Types
Problem Sets
Lecture Notes
Activity Assignments
Written Assignments
2D plot of degree six polynomials.
If f(x) has at most six zero crossings, we can find at most degree six polynomial that agrees with its sign. (Image by Prof. Ankur Moitra.)