Инд. авторы:	Ryabko D.B., Ryabko B.Y.
Заглавие:	Predicting the outcomes of every process for which an asymptotically accurate stationary predictor exists is impossible
Библ. ссылка:	Ryabko D.B., Ryabko B.Y. Predicting the outcomes of every process for which an asymptotically accurate stationary predictor exists is impossible // Proceedings of IEEE International Symposium on Information Theory (ISIT'15), 14-19 June 2015, Hong Kong. - 2015. - P.1204-1206. - http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7282646
Внешние системы:	DOI: 10.1109/ISIT.2015.7282646; РИНЦ: 27154124; SCOPUS: 2-s2.0-84969786555; WoS: 000380904701051;
Реферат:	eng: The problem of prediction consists in forecasting the conditional distribution of the next outcome given the past. Assume that the source generating the data is such that there is a stationary predictor whose error converges to zero (in a certain sense). The question is whether there is a universal predictor for all such sources, that is, a predictor whose error goes to zero if any of the sources that have this property is chosen to generate the data. This question is answered in the negative, contrasting a number of previously established positive results concerning related but smaller sets of processes.
Ключевые слова:	SEQUENCE; TIME-SERIES;
Издано:	2015
Физ. характеристика:	с.1204-1206
Ссылка:	http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7282646
Конференция:	Название: IEEE International Symposium on Information Theory Аббревиатура: ISIT'15 Город: Hong Kong Страна: China Даты проведения: 2015-06-14 - 2015-06-19
Цитирование:	1. D. Ryabko, "On the relation between realizable and non-realizable cases of the sequence prediction problem. " Journal of Machine Learning Research, vol. 12, pp. 2161-2180, 2011. 2. B. Ryabko, "Prediction of random sequences and universal coding, " Problems of Information Transmission, vol. 24, pp. 87-96, 1988. 3. D. H. Bailey, Sequential schemes for classifying and predicting ergodic processes. Department of Mathematics, Stanford University., 1976. 4. P. Algoet, "Universal schemes for prediction, gambling and portfolio selection, " The Annals of Probability, vol. 20, no. 2, pp. 901-941, 1992. 5. G. Morvai, S. Yakowitz, and L. Gyorfi, "Nonparametric inference for ergodic, stationary time series, " Ann. Statist, vol. 24, no. 1, pp. 370-379, 1996. 6. G. Morvai, S. Yakowitz, and P. Algoet, "Weakly convergent nonparametric forecasting of stationary time series, " Information Theory, IEEE Transactions on, vol. 43, no. 2, pp. 483-498, Mar. 1997. 7. L. Gyorfi, G. Morvai, and S. Yakowitz, "Limits to consistent on-line forecasting for ergodic time series, " IEEE Transactions on Information Theory, vol. 44, no. 2, pp. 886-892, 1998. 8. B. Ryabko, "Compression-based methods for nonparametric prediction and estimation of some characteristics of time series, " IEEE Transactions on Information Theory, vol. 55, pp. 4309-4315, 2009. 9. -, "Applications of universal source coding to statistical analysis of time series, " Selected Topics in Information and Coding Theory, World Scientific Publishing, pp. 289-338, 2010. 10. N. Cesa-Bianchi and G. Lugosi, Prediction, Learning, and Games. Cambridge University Press, 2006. 11. Y. Freund, "Predicting a binary sequence almost as well as the optimal biased coin, " Information and Computation, vol. 182, no. 2, pp. 73-94, 2003. 12. R. Gray, Probability, Random Processes, and Ergodic Properties. Springer Verlag, 1988. 13. A. N. Shiryaev, Probability. Springer, 1996.