This repository contains the practical session notebooks for the Mathematics of Machine Learning summer school.
DAY 1
| Activity | Topic |
|---|---|
| Lecture 1 | Introduction |
| Practical 1 | Robust One-Dimensional Mean Estimation |
| Lecture 2 | Concentration Inequalities. Bounds in Probability |
| Practical 2 | Model Selection Aggregation (Exercises 1-8) |
DAY 2
| Activity | Topic |
|---|---|
| Lecture 3 | Bernstein’s Concentration Inequalities. Fast Rates |
| Practical 3 | Model Selection Aggregation (Exercises 9-12) |
| Lecture 4 | Maximal Inequalities and Rademacher Complexity |
| Practical 4 | Offset Rademacher Complexity |
DAY 3
| Activity | Topic |
|---|---|
| Lecture 5 | Convex Loss Surrogates. Gradient Descent |
| Practical 5 | Optimization (Exercises 1-4) |
| Lecture 6 | Mirror Descent |
| Practical 6 | Optimization (Exercises 5-6) |
DAY 4
| Activity | Topic |
|---|---|
| Lecture 7 | Stochastic Methods. Algorithmic Stability |
| Practical 7 | Limitations of Gradient-Based Learning |
| Lecture 8 | Least Squares. Implicit Bias and Regularization |
| Practical 8 | Implicit Regularization |
DAY 5
| Activity | Topic |
|---|---|
| Lecture 9 | High-Dimensional Statistics. Gaussian Complexity |
| Practical 9 | Compressed Sensing |
| Lecture 10 | The Lasso Estimator. Proximal Gradient Methods |
| Practical 10 | Restricted Eigenvalue Condition |