Aims of the course

In machine learning, we are often interested in learning predictors and representations of some (high-dimensional) random variable. In contrast, causality allows us to additionally predict how the system underlying the data will respond to external manipulations. This has countless applications, including classic examples like epidemiology or econometrics, but also, more recently, AI for scientific discovery. In this course, we will cover three fundamentals of causal learning: inference, discovery, and representations. More concretely, we will first cover methods to estimate causal effects assuming known causal structure. Next, we will discuss how the causal structure itself can be learned from data. Finally, we will discuss the representation learning setting with high dimensional measurements. The course assumes no prior background in causality but requires statistics and machine learning background.

Content(sketch):

(1-2) Introduction, randomized trials, basic notions;
(3-4) Causal inference;
(5) Causal discovery;
(6) Causal representation learning.

Schedule:

• Monday 19/05/2025 16:30-18:30 – Room 1A150
• Tuesay 20/05/2025 16:30-18:30 – Room 1A150
• Wednesday 21/05/2025 16:30-18:30 – Room 1A150
• Thursday 22/05/2025 16:30-18:30 – Room 1A150
• Friday 23/05/2025 16:30-18:30 – Room 1A150