WS 24/25

Login: Please contact Ludwig Bothmann

Target group: Master Data Science

The field of machine learning has made remarkable advances, in particular with respect to predictive power. The broad usage of modern ML algorithms calls for further research targeting explainability and interpretability as well as fairness and robustness. Causal machine learning promises to play a crucial role in these research directions as it goes beyond purely associative relations between variables and allows to answer interventional and counterfactual questions.

Causal inference depends on a (given) causal model, typically represented by a causal graph, e.g. a Directed Acyclic Graph (DAG) whose directed edges and paths define direct and indirect causal effects. This seminar focuses on Causal Structure Learning (CSL) aka causal discovery which addresses the problem of revealing the causal graph from data.

The following review paper will serve as the common starting point:
Clark Glymour, Kun Zhang, and Peter Spirtes. Review of causal discovery methods based on graphical models. Frontiers in Genetics, 10:524, 2019.

password: fisher