Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Minimax Policies for Combinatorial Prediction Games Jean-Yves Audibert
 

Summary: Minimax Policies for Combinatorial Prediction Games
Jean-Yves Audibert
Imagine, Univ. Paris Est, and Sierra,
CNRS/ENS/INRIA, Paris, France
audibert@imagine.enpc.fr
S´ebastien Bubeck
Centre de Recerca Matem`atica
Barcelona, Spain
sbubeck@crm.cat
G´abor Lugosi
ICREA and Pompeu Fabra University
Barcelona, Spain
lugosi@upf.es
Abstract
We address the online linear optimization problem when the actions of the forecaster are repre-
sented by binary vectors. Our goal is to understand the magnitude of the minimax regret for the
worst possible set of actions. We study the problem under three different assumptions for the
feedback: full information, and the partial information models of the so-called "semi-bandit", and
"bandit" problems. We consider both L-, and L2-type of restrictions for the losses assigned by
the adversary.

  

Source: Audibert, Jean-Yves - Département d'Informatique, École Normale Supérieure

 

Collections: Computer Technologies and Information Sciences