Paper #282

Título:

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

Autores:

László Györfi, Gábor Lugosi y Gusztáv Morvai

Data:

Abril 1998

Resumen:

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 the sequence 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.

Palabras clave:

Prediction, ergodic processes, pattern classification

Códigos JEL:

C13

Área de investigación:

Estadística, Econometría y Métodos Cuantitativos

Publicado en:

IEEE Transactions on Information Theory, 45, (1999), pp. 2642-2650

Descargar el paper en formato PDF