Machine Learning Theory

This course presents theoretical and mathematical aspects of Machine Learning.

Topics to be covered include:

1. Introduction to the PAC formulation of learning,
2. Rademacher complexity and VC dimension,
3. Model selection,
4. Vector support machines (SVM),
5. Methods based on kernels (kernels),
6. Boosting,
7. Introduction to online learning,
8. Regression,
9. Ranking and multiclass classification,
9. Recent topics (depending on the teacher).

References:
Foundations of Machine Learning
Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar MIT Press, Second Edition, 2018.
Learning Theory from First Principles Francis Bach, https://www.di.ens.fr/~fbach/ltfp_book.pdf