Prediction, Learning, and Games

Nicolo Cesa-Bianchi, Gabor Lugosi

406 pages, parution le 01/05/2006

Ajouter à une liste

Indisponible

Résumé

This important new text and reference for researchers and students in machine learning, game theory, statistics and information theory offers the first comprehensive treatment of the problem of predicting individual sequences. Unlike standard statistical approaches to forecasting, prediction of individual sequences does not impose any probabilistic assumption on the data-generating mechanism. Yet, prediction algorithms can be constructed that work well for all possible sequences, in the sense that their performance is always nearly as good as the best forecasting strategy in a given reference class. The central theme is the model of prediction using expert advice, a general framework within which many related problems can be cast and discussed. Repeated game playing, adaptive data compression, sequential investment in the stock market, sequential pattern analysis, and several other problems are viewed as instances of the experts' framework and analyzed from a common nonstochastic standpoint that often reveals new and intriguing connections. Old and new forecasting methods are described in a mathematically precise way in order to characterize their theoretical limitations and possibilities.

First book to offer comprehensive treatment of the subject matter
Unifies different approaches developed in machine learning, game theory, statistics and information theory
Offers a self-contained introduction to the subject and presents the latest advances of the field

L'auteur - Gabor Lugosi

Gabor Lugosi is Professor at Universitat Pompeu Fabra in Barcelona.

Sommaire

Introduction
Prediction with expert advice
Tight bounds for specific losses
Randomized prediction
Efficient forecasters for large classes of experts
Prediction with limited feedback
Prediction and playing games
Absolute loss
Logarithmic loss
Sequential investment
Linear pattern recognition
Linear classification
Appendix

Voir tout

Replier

Caractéristiques techniques

	PAPIER
Éditeur(s)	Cambridge University Press
Auteur(s)	Nicolo Cesa-Bianchi, Gabor Lugosi
Parution	01/05/2006
Nb. de pages	406
Format	18 x 26
Couverture	Relié
Poids	873g
Intérieur	Noir et Blanc
EAN13	9780521841085
ISBN13	978-0-521-84108-5