Statistical Learning and Inference for Data Science (9+3hp)
New version of the course for 2023
Description
The process of learning models and inferring quantities lies at the heart of data science, including machine learning, signal processing and statistics. The goal of this graduate-level course is to provide a solid statistical foundation for researchers in data science. The course will tackle certain important issues that are not adequately addressed in conventional machine learning and statistics textbooks.
Course schedule
| Lec. | Date | Topics | Background reading |
|---|---|---|---|
| L1 | 2020-09-24 @ 10.15 | Fundamental concepts in statistical learning | (W: 1, 2, 3) W: 6, 4, 5. |
| L2 | 2020-10-01 @ 10.15 | Confidence sets, model learning | W: 6.3.2, 8, 9 |
| L3 | 2020-10-15 @ 10.15 | Model validation, Bayesian regularization, | W: 11 |
| L4 | 2020-10-22 @ 10.15 | Robust learning, Regression | W: 13, 14 |
| L5 | 2020-11-12 @ 10.15 | Classification | W: 22, 10 |
| L6 | 2020-11-19 @ 10.15 | Causal structures of DGPs | W: 16, 17 |
| L7 | 2020-11-26 @ 10.15 | Causal inference | TBA |
| L8 | 2020-12-03 @ 10.15 | Summary | TBA |
Background readings (W) from Larry Wasserman's book All of Statistics.
Examination
- Weekly homeworks (9hp)
- Voluntary project corresponding to a three-page research paper (3hp)
Prerequisites
Undergraduate courses in linear algebra and probability theory.
Registration
E-mail the course responsible.