MATH 789R - Reading Seminar on Mathematics of Machine Learning

Course Summary

Recent developments in machine learning have led to breakthroughs in applications such as speech and image recognition. These tools have also been used to solve challenging mathematical problems, e.g., high-dimensional PDEs, control problems, integral, or eigenvalue problems.

Despite the many success stories we see in the news and many theoretical advances that have already been made, our theoretical understanding of some machine learning tools is still very limited. As in other areas of science, the language of mathematics has been showing to gain a deeper understanding of machine learning.

In this seminar, we will discuss recent works at the interface of mathematics and machine learning with the goal of exposing new research questions.

Expectations and Grading

The class provides 3 credit hours for students that enroll on an S/U basis. I expect students to participate in the following ways:


Students are expected to read each paper from the reading list before participating in online and in-class discussions.

Online Discussions

There is one asynchronous online discussion per week that covers the paper discussed in the seminar. Students need to post one answer to the discussion prompt (typically due by Friday) and provide a constructive comment to at least one other post (typically due by Tuesday). Although I will grade the posts only as complete/incomplete, you may find it helpful to consider this sample rubric while working on these assignments. One incomplete or late survey will be tolerated.


Each student must moderate the discussion of at least one paper of their choice assigned on a first-come-first-serve basis. This entails proposing one or two questions for the online discussion and designing the synchronous session. Each session should start with a short (10-15 minute) presentation that summarizes the paper and common threads of the online discussion. The remaining time can be used in various ways and should include some active elements such as discussion in breakout sessions, quizzes, creation of online material. I will help in the preparation process and expect the presenter to send me a complete draft of their slides and a roadmap for the session at least one week before the presentation. Students that want to take the class need to select a paper in the first week of classes.

Lars Ruthotto
Lars Ruthotto
Winship Distinguished Research Associate Professor of Mathematics and Computer Science