A simple randomized algorithm for consistent sequential prediction of ergodic time series

All of RECERCAT

To access the full text documents, please follow this link: http://hdl.handle.net/10230/922

Title:	A simple randomized algorithm for consistent sequential prediction of ergodic time series
Author:	Györfi, László; Lugosi, Gábor; Morvai, Gusztáv
Other authors:	Universitat Pompeu Fabra. Departament d'Economia i Empresa
Abstract:	We present a simple randomized procedure for the prediction of a binary sequence. The algorithm uses ideas from recent developments of the theory of the prediction of individual sequences. We show that if thesequence is a realization of a stationary and ergodic random process then the average number of mistakes converges, almost surely, to that of the optimum, given by the Bayes predictor.
Subject(s):	-prediction -ergodic processes -pattern classification -Statistics, Econometrics and Quantitative Methods
Rights:	L'accés als continguts d'aquest document queda condicionat a l'acceptació de les condicions d'ús establertes per la següent llicència Creative Commons http://creativecommons.org/licenses/by-nc-nd/3.0/es/
Document type:	Working Paper
Share: