Sequential Prediction of Unbounded Stationary Time Series

Sequential Prediction of Unbounded Stationary Time Series

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 sur...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on information theory 2007-05, Vol.53 (5), p.1866-1872
Hauptverfasser: Gyorfi, L., Ottucsak, G.
Format: Artikel
Sprache:eng
Schlagworte:
Algorithms
Applied sciences
Automation
Bayesian analysis
Binary system
Classification
Convergence
Economic forecasting
Exact sciences and technology
High-speed networks
Informatics
Information theory
Information, signal and communications theory
On-line learning
On-line systems
Optimization
Pattern recognition
Predictions
Random processes
Random variables
sequential prediction
Signal processing
Statistical learning
Telecommunication computing
Telecommunications and information theory
Time series
universal consistency
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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
ISSN:0018-9448
1557-9654
DOI:10.1109/TIT.2007.894660