Title :

Bandits on graphs and structures

English title :

Bandits on graphs and structures

Author(s) :

Valko, Michal [Auteur]
Sequential Learning [SEQUEL]

Thesis director(s) :

Aurélien Garivier

Defence date :

2016-06-15

Jury president :

Nicolas Vayatis (Garant & Examinateur)
Aurélien Garivier (Président & Rapporteur)
Gábor Lugosi (Rapporteur)
Vianney Perchet (Rapporteur)
Nicolò Cesa-Bianchi (Examinateur)
Mark Herbster (Examinateur)
Rémi Munos (Examinateur)

Jury member(s) :

Nicolas Vayatis (Garant & Examinateur)
Aurélien Garivier (Président & Rapporteur)
Gábor Lugosi (Rapporteur)
Vianney Perchet (Rapporteur)
Nicolò Cesa-Bianchi (Examinateur)
Mark Herbster (Examinateur)
Rémi Munos (Examinateur)

Accredited body :

École normale supérieure de Cachan - ENS Cachan

Keyword(s) :

apprentissage statistique

English keyword(s) :

machine learning
sequential decision-making
bandits
graphs
structured learning

HAL domain(s) :

Statistiques [stat]/Machine Learning [stat.ML]

English abstract : [en]

We investigate the structural properties of certain sequential decision-making problems with limited feedback (bandits) in order to bring the known algorithmic solutions closer to a practical use. In the first part, we put ...
Show more >We investigate the structural properties of certain sequential decision-making problems with limited feedback (bandits) in order to bring the known algorithmic solutions closer to a practical use. In the first part, we put a special emphasis on structures that can be represented as graphs on actions, in the second part we study the large action spaces that can be of exponential size in the number of base actions or even infinite. We show how to take advantage of structures over the actions and (provably) learn faster.Show less >

Language :

Anglais

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL