Name
Abstract | ||
|---|---|---|
A simple on-line procedure is considered for the prediction of a real-valued sequence. The algorithm is based on a combination of several simple predictors. If the sequence is a realization of an unbounded stationary and ergodic random process then the average of squared errors converges, almost surely, to that of the optimum, given by the Bayes predictor. An analog result is offered for the classification of binary processes |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1109/TIT.2007.894660 | IEEE Transactions on Information Theory |
Keywords | Field | DocType |
Bayes methods,binary sequences,pattern classification,prediction theory,random processes,time series,Bayes predictor,binary process,ergodic random process,real-valued sequential prediction,stationary time series,On-line learning,pattern recognition,sequential prediction,time series,universal consistency | Applied mathematics,Discrete mathematics,Ergodicity,Ergodic process,Ergodic theory,Stochastic process,Almost surely,Stationary sequence,Statistics,Mathematics,Bayes' theorem,Binary number | Journal |
Volume | Issue | ISSN |
53 | 5 | 0018-9448 |
Citations | PageRank | References |
14 | 1.09 | 9 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| László Györfi | 1 | 17 | 2.86 |
| Ottucsak, G. | 2 | 14 | 1.09 |