PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Strategies for prediction under imperfect monitoring.
Gábor Lugosi, Shie Mannor and Gilles Stoltz
Mathematics of Operations Research Volume to appear, 2008.

Abstract

We propose simple randomized strategies for sequential decision (or prediction) under imperfect monitoring, that is, when the decision maker (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 among all fixed actions. It was Rustichini [26] 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 signals, these rates are optimal up to logarithmic terms.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:3925
Deposited By:Gábor Lugosi
Deposited On:25 February 2008