Abstract
For Gaussian process, we present an open problem whether or not there is a data driven predictor of the conditional expectation of the current value given the past such that the difference between the predictor and the conditional expectation tends to zero almost surely for all stationary, ergodic, Gaussian processes. We show some related negative and positive findings.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Algoet, P.: The strong law of large numbers for sequential decisions under uncertainty. IEEE Trans. Inf. Theory 40, 609–634 (1994)
Alquier, P., Wintenberger, O.: Model selection for weakly dependent time series forecasting. Bernoulli 18, 883–913 (2012)
Bailey, D.H.: Sequential schemes for classifying and predicting ergodic processes. PhD thesis, Stanford University (1976)
Bierens, H.J.: The Wold decomposition. Manuscript (2012). http://econ.la.psu.edu/~hbierens/WOLD.PDF
Bleakley, K., Biau, G., Györfi, L., Ottucs, G.: Nonparametric sequential prediction of time series. J. Nonparametr. Stat. 22, 297–317 (2010)
Brockwell, P., Davis, R.A.: Time Series: Theory and Methods, 2nd edn. Springer, New York (1991)
Buldygin, V.V., Donchenko, V.S.: The convergence to zero of Gaussian sequences. Matematicheskie Zametki 21, 531–538 (1977)
Cornfeld, I., Fomin, S., Sinai, Y.G.: Ergodic Theory. Springer, New York (1982)
Doob, J.L.: The elementary Gaussian processes. Ann. Math. Stat. 15, 229–282 (1944)
Feller, W. An Introduction to Probability and Its Applications, vol. 1. Wiley, New York (1957)
Gerencsér, L.: AR(∞) estimation and nonparametric stochastic complexity. IEEE Trans. Inf. Theory 38, 1768–1779 (1992)
Gerencsér, L.: On Rissanen’s predictive stochastic complexity for stationary ARMA processes. J. Stat. Plan. Inference 41, 303–325 (1994)
Gerencsér, L., Rissanen, J.: A prediction bound for Gaussian ARMA processes. In: Proc. of the 25th Conference on Decision and Control, pp. 1487–1490 (1986)
Grenander, U.: Stochastic processes and statistical inference. Arkiv Math. 1, 195–277 (1950)
Györfi, L.: Adaptive linear procedures under general conditions. IEEE Trans. Inf. Theory 30, 262–267 (1984)
Györfi, L. and Lugosi, G.: Strategies for sequential prediction of stationary time series. In: Dror, M., L’Ecuyer, P., Szidarovszky, F. (eds.) Modelling Uncertainty: An Examination of its Theory, Methods and Applications, pp. 225–248. Kluwer, Boston (2001)
Györfi, L., Morvai, G., Yakowitz, S.: Limits to consistent on-line forecasting for ergodic time series. IEEE Trans. Inf. Theory 44, 886–892 (1998)
Györfi, L., Ottucsák, G.: Sequential prediction of unbounded time series. IEEE Trans. Inf. Theory 53, 1866–1872 (2007)
Inoue, A.: AR and MA representations of partial autocorrelation functions, with applications. Probab. Theory Relat. Fields 140, 523–551 (2008)
Isserlis, L.: On a formula for the product-moment coefficient of any order of a normal frequency distribution in any number of variables. Biometrika 12, 134–39 (1918)
Karlin, S., Taylor, H.M.: A First Course in Stochastic Processes. Academic Press, New York (1975)
Klimo, L.A. Nelson, P.I.: On conditional least squares estimation for stochastic processes. Ann. Stat. 6, 629–642 (1978)
Lindgren, G.: Lectures on Stationary Stochastic Processes. Lund University (2002). http://www.maths.lu.se/matstat/staff/georg/Publications/lecture2002.pdf
Maruyama, G.: The harmonic analysis of stationary stochastic processes. Mem. Fac. Sci. Kyusyu Univ. A4, 45–106 (1949)
McDonald, D.J., Shalizi, C.R., Schervish, M.: Generalization error bounds for stationary autoregressive models (2012). http://arxiv.org/abs/1103.0942
Meir, R.: Nonparametric time series prediction through adaptive model selection. Mach. Learn. 39, 5–34 (2000)
Ninness, B.: Strong laws of large numbers under weak assumptions with application. IEEE Trans. Autom. Control 45, 2117–2122 (2000)
Pisier, G.: Probabilistic methods in the geometry of Banach spaces. In: Probability and Analysis. Lecture Notes in Mathematics, vol. 1206, pp. 167–241. Springer, New York (1986)
Ryabko, B.Y.: Prediction of random sequences and universal coding. Probl. Inf. Transm. 24, 87–96 (1988)
Schäfer, D.: Strongly consistent online forecasting of centered Gaussian processes. IEEE Trans. Inf. Theory 48, 791–799 (2002)
Acknowledgements
This work was partially supported by the European Union and the European Social Fund through project FuturICT.hu (grant no.: TAMOP-4.2.2.C-11/1/KONV-2012-0013).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer Science+Business Media New York
About this paper
Cite this paper
Györfi, L., Sancetta, A. (2014). An Open Problem on Strongly Consistent Learning of the Best Prediction for Gaussian Processes. In: Akritas, M., Lahiri, S., Politis, D. (eds) Topics in Nonparametric Statistics. Springer Proceedings in Mathematics & Statistics, vol 74. Springer, New York, NY. https://doi.org/10.1007/978-1-4939-0569-0_12
Download citation
DOI: https://doi.org/10.1007/978-1-4939-0569-0_12
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4939-0568-3
Online ISBN: 978-1-4939-0569-0
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)