Strategies for prediction under imperfect monitoring

Abstract : We propose simple randomized strategies for sequential prediction under imperfect monitoring, that is, when the forecaster does not have access to the past outcomes but rather to a feedback signal. The proposed strategies are consistent in the sense that they achieve, asymptotically, the best possible average reward. It was Rustichini (1999) who first proved the existence of such consistent predictors. The forecasters presented here offer the first constructive proof of consistency. Moreover, the proposed algorithms are computationally efficient. We also establish upper bounds for the rates of convergence. In the case of deterministic feedback, these rates are optimal up to logarithmic terms.
Type de document :
Article dans une revue
Mathematics of Operations Research, INFORMS, 2008, à paraître
Liste complète des métadonnées

Littérature citée [29 références]  Voir  Masquer  Télécharger
Contributeur : Gilles Stoltz <>
Soumis le : lundi 7 janvier 2008 - 15:03:46
Dernière modification le : mardi 24 avril 2018 - 17:20:06
Document(s) archivé(s) le : vendredi 25 novembre 2016 - 18:32:14





Gabor Lugosi, Shie Mannor, Gilles Stoltz. Strategies for prediction under imperfect monitoring. Mathematics of Operations Research, INFORMS, 2008, à paraître. 〈hal-00124679v4〉



Consultations de la notice


Téléchargements de fichiers