Fiche du document
2008
- handle: 10670/1.byno0o
- hal: hal-00124679
- ARXIV: math/0701419
Ce document est lié à :
info:eu-repo/semantics/altIdentifier/arxiv/math/0701419
info:eu-repo/semantics/OpenAccess
Mots-clés
individual sequences repeated games with partial monitoring approachability MSC: 91A20, 62L12, 68Q32Sujets proches
Prediction Forecasts FuturologyCiter ce document
Gabor Lugosi et al., « Strategies for prediction under imperfect monitoring », HALSHS : archive ouverte en Sciences de l’Homme et de la Société, ID : 10670/1.byno0o
Métriques
Partage / Export
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.