Strategies for prediction under imperfect monitoring - HAL-SHS - Sciences de l'Homme et de la Société Accéder directement au contenu
Article Dans Une Revue Mathematics of Operations Research Année : 2008

Strategies for prediction under imperfect monitoring

Résumé

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.
Fichier principal
Vignette du fichier
LugosiMannorStoltz-Final.pdf (312.47 Ko) Télécharger le fichier
INFORMS.ps (77.26 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Format : Autre
Loading...

Dates et versions

hal-00124679 , version 1 (15-01-2007)
hal-00124679 , version 2 (21-04-2007)
hal-00124679 , version 3 (12-07-2007)
hal-00124679 , version 4 (07-01-2008)

Identifiants

Citer

Gabor Lugosi, Shie Mannor, Gilles Stoltz. Strategies for prediction under imperfect monitoring. Mathematics of Operations Research, 2008, à paraître. ⟨hal-00124679v4⟩
640 Consultations
253 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More