Sequential Learning (Orsay)

M2 Mathématique de l'Aléatoire & Mathématiques et Intelligence Artificielle, Université Paris-Saclay, 2023-ongoing

Sequential Learning course for Master 2 Mathématiques de l’Aléatoire & MathIA.

Year 2026-2027

Courses are every Tuesday, 2pm-5pm in room 1A12, starting from September 29, until December 1st.

Note: there is no course on October 6 and October 27.

Due to student protests, there will be no class on Tuesday, October 20. The next class will take place (hopefully) on November 3rd.

Course Evaluation

1 homework (20%)
1 final written exam (80%)

The homework is available here. It is currently due on November 25. Before Lecture 3, you should only look at the Exercise 1.

Each student is allowed a single handwritten, two-sides, cheatsheet for the exam. Exam will be on December 15 at 2pm in room 0A4.

Lecture Notes

Lecture 1 (learning with experts)
Lecture 2 (concentration inequalities)
Lecture 3 (stochastic bandits, part 1)
Lecture 4 (stochastic bandits, part 2)
Lecture 5 (lower bound)
Lecture 6 (MOSS and continuum of arms)
Lecture 7 (contextual linear bandits)
Lecture 8 (pure exploration)
Exercise sheet n°1 (lectures 1 to 4)
Exercise sheet n°2 (lectures 5 to 8)

Bibliographic Resources

Bandit algorithms, Tor Lattimore and Csaba Szepesvári. Cambridge University Press, 2020.
Introduction to Multi-Armed Bandits, Aleksandrs Slivkins. In Foundations and Trends in Machine Learning, 2019.