Universal prediction of random binary sequences in a noisy environment

Annals of Applied Probability

Volumn 14, Issue 1, 2004, Pages 54-89

  Weissman, Tsachy ^a,c   Merhav, Neri ^b  

^a STANFORD UNIVERSITY   (United States)

^b TECHNION ISRAEL INSTITUTE OF TECHNOLOGY   (Israel)

^c Stanford University   (United States)

Author keywords

Asymptotic optimality; Conditional mixing; Filtering; Generalized ergodic theorem; Martingale difference; Prediction; Prediction with experts; Prediction with noise; Sequential decisions; Shannon entropy; Universal

Indexed keywords

EID: 12444347037     PISSN: 10505164     EISSN: 10505164     Source Type: Journal    
DOI: 10.1214/aoap/1075828047     Document Type: Article

References (21)

1. ALGOET, P. H. (1994). The strong law of large numbers for sequential decisions under uncertainty. IEEE Trans. Inform. Theory 40 609-634.
2. ATAR, R. and ZEITOUNI, O. (1997). Lyapunov exponents for finite state nonlinear filtering. SIAM J. Control Optim. 35 36-55.
3. BREIMAN, L. (1973). A note on minimax filtering. Ann. Probab. 1 175-179.
4. BREIMAN, L. (1992). Probability. SIAM, Philadelphia, PA.
5. CASTELLI, V. and COVER, T. M. (1995). On the exponential value of labeled samples. Pattern Recognition Letters 16 105-111.
6. CHEN, C. and KASSAM, S. A. (1984). Robust Wiener filtering for multiple inputs with channel distortion. IEEE Trans. Inform. Theory 30 674-677.
7. FEDER, M., MERHAV, N. and GUTMAN, M. (1992). Universal prediction of individual sequences. IEEE Trans. Inform. Theory 38 1258-1270.
8. FRANKE, J. (1985). Minimax: Robust prediction of discrete time series. Z. Wahrsch. Verw. Gebiete 68 337-364.
9. GYÖRFI, L. and LUGOSI, G. (2001). Strategies for sequential prediction of stationary time-series. In Modeling Uncertainty: An Examination of Its Theory, Methods, and Applications (M. Dror, P. L'Ecuyer and F. Szidarovszky, eds.). Kluwer, Dordrecht.
10. GYÖRFI, L., LUGOSI, G. and MORVAI, G. (1999). A simple randomized algorithm for sequential prediction of ergodic time series. IEEE Trans. Inform. Theory 45 2642-2650.
11. HALL, P. and HEYDE, C. C. (1980). Martingale Limit Theory and Its Application. Academic Press, New York.
12. HAUSSLER, D., KIVINEN, J. and WARMUTH, M. K. (1998). Sequential prediction of individual sequences under general loss functions. IEEE Trans. Inform. Theory 44 1906-1925.
13. KASSAM, S. A. and LIM, T. L. (1977). Robust Wiener filters. J. Franklin Inst. 304 171-185.
14. KASSAM, S. A. and POOR, H. V. (1985). Robust Techniques for Signal Processing: A Survey. Proceedings of the IEEE 73.
15. MERHAV, N. and FEDER, M. (1998). Universal prediction. IEEE Trans. Inform. Theory 44 2124-2147.
16. VASTOLA, K. S. and POOR, H. V. (1984). Robust Wiener-Kolmogorov theory. IEEE Trans. Inform. Theory 30 316-327.
17. VOVK, V. (1990). Aggregating strategies. In Proc. Third Annual Workshop on Computational Learning Theory 371-383. Kaufmann, San Mateo, CA.
18. VOVK, V. (1995). A game of prediction with expert advice. In Proc. Eighth Annual Workshop on Computational Learning Theory 51-60. ACM Press, NY.
19. WEISSMAN, T. and MERHAV, N. (2001). Universal prediction of individual binary sequences in the presence of noise. IEEE Trans. Inform. Theory 47 2151-2173.
20. WEISSMAN, T., MERHAV, N. and BARUCH, A. (2001). Twofold universal prediction schemes for achieving the finite-state predictability of a noisy individual binary sequence. IEEE Trans. Inform. Theory 47 1849-1866.
21. ZIV, J. and LEMPEL, A. (1978). Compression of individual sequences via variable rate coding. IEEE Trans. Inform. Theory 24 530-536.