Registration Deadline: January 24, 2027

Instructor: Professor Sebastian Ferrando, Toronto Metropolitan University

Course Dates: 
Mid-Semester Break: 
Lecture Time: 
Office Hours: 

Registration Fee:

• Students from our Principal Sponsoring & Affiliate Universities: Free
• Other Students: CAD$500

Capacity Limit: 

Format: 

Course Description

This course provides a mathematically grounded introduction to causal inference centered on the directed graph framework developed by Judea Pearl. The presentation starts from basic but realistic causal examples formulated on directed graphs and from the concrete questions they raise. The focus is on elucidating the mathematical structures that support causal reasoning and justify causal conclusions in these settings.

The course develops the theory of directed graphs, conditional independence, and graphical separation, and examines how these concepts underpin identification of causal effects under interventions and counterfactual reasoning. Particular attention is given to isolating the precise hypotheses required at each step, and to understanding how causal conclusions depend on structural and informational assumptions.

Beyond static graphical models, the course introduces additional mathematical tools inspired by stochastic analysis and robust financial mathematics, including time-indexed information structures and portfolio-style representations, to rephrase and refine intervention questions in a dynamic and, in part, non-probabilistic setting.

Assessment is project-based, with students completing technical presentations accompanied by written reports. Selected topics at the interface of causality, adversarial learning, and game theory are presented, and students will explore contemporary research directions connecting causal reasoning with modern artificial intelligence.