- February 3rd and 10th, 2021 "DYNAMICS IN GAMES: ALGORITHMS AND LEARNING"
Sylvain Sorin Website
Game theory studies interactions between agents with specific aims, be they rational actors, genes, or computers. This course is intended to provide the main mathematical concepts and tools used in game theory with a particular focus on their connections to learning and convex optimization. The first part of the course deals with the basic notions: value, (Nash and Wardrop) equilibria, correlated equilibria. We will give several dynamic proofs of the minmax theorem and describe the link with Blackwell’s approachability. We will also study the connection with variational inequalities.
The second part will introduce no-regret properties in on-line learning and exhibit a family of unilateral procedures satisfying this property. When applied in a game framework we will study the consequences in terms of convergence (value, correlated equilibria). We will also compare discrete and continuous time approaches and their analog in convex optimization (projected gradient, mirror descent, dual averaging). Finally we will present the main tools of stochastic approximation that allows to deal with random trajectories generated by the players.
Lectures here :
Morning lecture, Feb 3, 2021
Afternoon lecture, Feb 3, 2021
Morning lecture, Feb 10, 2021
Afternoon lecture, Feb 10, 2021
- September 10-11, 2020 PGMO Lecture "Algorithmic game theory : from multi-agent optimization to online learning"
(Universidad Adolfo Ibáñez, Santiago) - Biographie
(LIG, Grenoble) - Biographie
A satellite event of the SMAI-MODE 2020 conference organized jointly with GDR MOA.
The summary can be found on: https://smai-mode2020.inria.fr/en/mini-cours/
The Dodu prize for the best communication of a young researcher at the conference
SMAI-MODE 2020 https://smai-mode2020.inria.fr/, has been awarded to Anas BARAKAT (Telecom Paris) et Bento NATURA (London School of Economics) ,
ex-aequo. This prize is sponsored by EDF within the setting of PGMO. Congratulations to the laureates !
The schedule of the lecture is the following
Thursday, September 10th, 11h00-12h30
Download: Introduction, Lecture 1
Thursday, September 10th, 13h30-15h00
Download: Lecture 2
Thursday, September 10th, 15h30-17h00
Download: Lecture 3
Vidéos Cours PGMO-MOA-MODE : https://www.youtube.com/playlist?list=PLQERYuTxSzGYfm_vvmjqJ3ZVev1J-XYdH
- February 12-13, 2020 Thomas POCK "Vision, Optimization and Learning"
The links to the slides and the notebooks can be found at the bottom right of the page : https://indico.math.cnrs.fr/event/5381/