Cours/Séminaire
Notice
Lieu de réalisation
École Normale Supérieure, Paris, France.
Langue :
Anglais
Crédits
Claire Boyer (Production), Djalil Chafaï (Production), Joseph Lehec (Production), Sébastien Bubeck (Intervention)
Conditions d'utilisation
Droit commun de la propriété intellectuelle
DOI : 10.60527/xdfj-x289
Citer cette ressource :
Sébastien Bubeck. CEREMADE. (2019, 3 juillet). Bubeck 5/9 - Some geometric aspects of randomized online decision making. [Vidéo]. Canal-U. https://doi.org/10.60527/xdfj-x289. (Consultée le 2 juin 2024)

Bubeck 5/9 - Some geometric aspects of randomized online decision making

Réalisation : 3 juillet 2019 - Mise en ligne : 3 novembre 2019
  • document 1 document 2 document 3
  • niveau 1 niveau 2 niveau 3
Descriptif

This course is concerned with some of the canonical non-stochastic models of online decision making. These models have their origin in works from the 1950's and 1960's, and went through a resurgence in the mid-2000's due to many applications in the internet economy. This course focuses on a set of challenging conjectures around these models from the 1980's and 1990's. We present a unified approach based on a combination of convex optimization techniques together with powerful probabilistic tools, which will allow us to derive state of the art results in online learning, bandit optimization, as well as some classical online computing problems (k-server and metrical task systems). Special emphasis are given to proper introduction of the mathematical/algorithmic tools: gradient descent, mirror descent (i.e., Riemannian gradient descent), probabilistic embedding of metric spaces, some basic results in convex geometry, etc.

Intervention

Avec les mêmes intervenants et intervenantes

Sur le même thème