Sequential Prediction of Unbounded Stationary Time Series

  title={Sequential Prediction of Unbounded Stationary Time Series},
  author={L. Gyorfi and Gy{\"o}rgy Ottucs{\'a}k},
  journal={IEEE Transactions on Information Theory},
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 
Highly Cited
This paper has 34 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.
19 Citations
27 References
Similar Papers


Publications citing this paper.


Publications referenced by this paper.
Showing 1-10 of 27 references

Strategies for sequential prediction of stationary time series

  • L. Györfi, G. Lugosi
  • inModelling Uncertainty: An Examination of its…
  • 2001
Highly Influential
15 Excerpts

Probabilistic Theory of Pattern Recognition

  • L. Devroye, L. Gÿorfi, A G. Lugosi
  • 1996
Highly Influential
10 Excerpts

Universal schemes for prediction, gambling, and por tfolio selection,”Annals

  • P. Algoet
  • of Probability,
  • 1992
Highly Influential
9 Excerpts

Local convergence of martingales and the law of larg e numbers,”Annals of Mathematical Statistics

  • Y. S. Chow
  • 1965
Highly Influential
3 Excerpts

Similar Papers

Loading similar papers…