Paper #282
- Title:
- A simple randomized algorithm for consistent sequential prediction of ergodic time series
- Authors:
- László Györfi, Gábor Lugosi and Gusztáv Morvai
- Date:
- April 1998
- 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.
- Keywords:
- Prediction, ergodic processes, pattern classification
- JEL codes:
- C13
- Area of Research:
- Statistics, Econometrics and Quantitative Methods
- Published in:
- IEEE Transactions on Information Theory, 45, (1999), pp. 2642-2650
Download the paper in PDF format