"Towards causal representation learning"., Schölkopf et al. Proceedings of the IEEE 2021

Announcements

Assignment

The problem set is released. It is due on October 31, 11:59 pm ET.

October 9, 2022

COVID-19

Although the pandemic has diminished somewhat, all indications are that we are not yet out of the woods. The university no longer requires the use of masks on its premises but encourages it where it is impossible to maintain physical distancing, such as in classrooms and offices.

We strongly recommend that you continue to wear masks during lectures, tutorials, and office hours out of consideration for the health of others. We also strongly encourage you to get vaccine booster shots whenever possible. The instructors plan to wear masks when in close proximity with students, such as when answering questions after lectures or during office hours. However, we may take off our masks when lecturing if we are at a safe distance from students.

September 12, 2022

Course Description

There is an increasing interest in using machine learning to solve problems in causal inference and the use of causal inference to design new machine learning algorithms. In this course, we will discuss the difference between statistical and causal estimands and introduce assumptions and models that allow estimating causal queries. It will be a mixed lecture/assignment/seminar/project-based course. Students will learn the basic concepts, nomenclature, and results in causality, along with advanced material characterizing recent applications of causality in machine learning. The motivating examples for the course material will be the application of machine learning to problems in healthcare. Students must have a strong background in probability theory, statistics, Bayesian networks, and familiarity with linear algebra and latent variable modeling.