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

Györfi, László; Lugosi, Gábor; Morvai, Gusztáv

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

License

Citation

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

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 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.