PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Minimizing Regret with Label Efficient Prediction
Nicolò Cesa-Bianchi, Gábor Lugosi and Gilles Stoltz
IEEE Transactions on Information Theory Volume 51, pp. 2152-2162, 2005.

This is the latest version of this eprint.

Abstract

We investigate label efficient prediction, a variant, proposed by Helmbold and Panizza, of the problem of prediction with expert advice. In this variant the forecaster, after guessing the next element of the sequence to be predicted, does not observe its true value unless he asks for it, which he cannot do too often. We determine matching upper and lower bounds for the best possible excess prediction error, with respect to the best possible constant predictor, when the number of allowed queries is fixed. We also prove that Hannan consistency, a fundamental property in game-theoretic prediction models, can be achieved by a forecaster issuing a number of queries growing to infinity at a rate just slightly faster than logarithmic in the number of prediction rounds.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:1116
Deposited By:Gábor Lugosi
Deposited On:13 October 2005

Available Versions of this Item