Admission requirements
In order to be successful in this course, it is recommended to have a basic knowledge of:
Discrete math
Statistics (basic probability, modeling, and experimental design)
Machine learning (graphical models)
Programming experience in python
Description
In the field of machine learning, you may need to predict the impact of action on an outcome by analyzing a huge amount of collected data. Unfortunately, this data is often of low quality, with missing records, unobserved confounders, and selection biases. As a result, answering questions about the impact of an action becomes more difficult than ever. This course covers mathematical tools to help you perfrom causal inference in big data. We will use sturctural causal models, and potential outcomes to formalize what causal effects mean, explain how to express these effects as functions of observed data, and use machine learning techniques to estimate them. We will also cover causal structure learning algorithms to recover causal relationships from data, and discurss applications of causality in other fields in machine learning (such as reinforcement learning and natural language processing).
In the course, we cover the following topics:
Structural causal models (SCM), Potential outcome (PO) framework
Interventions, Counterfactuals
The tasks of causal discovery and causal inference (the bivariate case)
Causal discovery (the multivariate case): ** D-separation, Markov equivalence class ** Constraint-based methods (IC, PC, and FCI) ** Score-based methods (GES) ** Learning from time-series (Granger causality, Directed information)
Causal inference: ** Instrumental variables ** Natural experiments ** Back-door criterion, Front-door criterion ** Do-calculus ** IP weighting, Propensity scores
Applications of causality
Course objectives
At the end of the course, the student is able to:
translate causal queries described in words to mathematical ones.
explain the two main frameworks for causal inference (SCM and PO frameworks) and know how to use them in a causal inference task.
analyze common causal discovery algorithms (such as PC and GES) and explain their assumptions.
apply causal discovery algorithms on the data and evaluate the outcomes.
analyze common causal inference algorithms (such as do-calculus, difference-in-difference,...) and explain their underlying assumptions.
apply the suitable causal inference method according to the causal query.
Timetable
Mode of instruction
20 sessions of lecture and four sessions of working group.
Assessment method
There are a written exam, three assignments, and a presentation of a research paper (reproducing the results) in the course. The assignments can be completed and submitted during the semester according to the deadlines.
The weighting of the final grade will be:
20% Presentation
30% Assignments
50% Final exam
Students can use any material in submitting the assignments but they are responsible for the entire content of the assignment. Students may be randomly selected to discuss the approach they used in their assignments. It is allowed to retake the final exam (not the assignments and the presentations) if a student cannot pass the course. The research paper for the presentation part should be presented individually. The topic of the research paper can be selected from a given list or suggested by students (in this case, it is required to check the quality of the paper with the instructor).
Reading list
- Jonas Peters, Dominik Janzing, and Bernhard Schölkopf. Elements of Causal Inference:
Foundations and Learning Algorithms. MIT press, 2018. - Judea Pearl. Causality. Cambridge university press, 2009.
- Judea Pearl, Madelyn Glymour, and Nicholas P. Jewell. Causal inference in statistics: a
primer. John Wiley & Sons, 2016. - Peter Spirtes, Clark N. Glymour, and Richard Scheines. Causation, prediction, and search.
MIT press, 2000. - Miguel A. Hernan, James M. Robins. Causal Inference: What If. Chapman & Hall/CRC, 2020.
Registration
Contact
In case you have any questions about the course, please send an email to the following email address: s.salehkaleybar@liacs.leidenuniv.nl