Syllabus

1. Introduction
2. The Nearest Neighbour algorithm
3. Tree predictors
4. Statistical learning
5. Risk analysis for tree predictors
6. Hyperparameter tuning and risk estimates
7. Consistency and nonparametric algorithms
8. Risk analysis for Nearest Neighbour
9. Linear predictors
10. Online gradient descent
11. Kernel functions
12. Support Vector Machines
13. Stability and risk control for SVM
14. Neural networks and deep learning
15. Logistic regression and surrogate loss functions
16. Boosting and ensemble methods

Graduate

48

Semester Course

The final grade is the arithmetic average (rounded to the nearest integer) of the mark obtained in the written test and the mark obtained in the project. The exam is passed if: the average is 18 or higher and both marks are 17 or higher.

Free to anyone. Maximal registrant number: 10 students. If you are an AIDA Student* already, please: Step (a): Register in the course by sending an email to the Course Lecturer for your registration. AND Step (b): Enroll in the same course in the AIDA course link using the ‘Enroll on this course’ button therein, so that this course enters your AIDA Certificate of Course Attendance. If you are not an AIDA Student do only step (a). *AIDA Students should have been registered in the AIDA system already (they are PhD students or PostDocs that belong only to the AIDA Members listed in this page: Members)

Every Monday 14:30-16:30 and Tuesday 11:30-13:30

English

In person

https://cesa-bianchi.di.unimi.it/MSA/index_23-24.html