Nonparametric time series prediction through adaptive model selection

Machine Learning

Volumn 39, Issue 1, 2000, Pages 5-34

  Meir, Ron ^a  

^a TECHNION ISRAEL INSTITUTE OF TECHNOLOGY   (Israel)

Author keywords

[No Author keywords available]

Indexed keywords

ADAPTIVE SYSTEMS; COMPUTATIONAL COMPLEXITY; ERROR ANALYSIS; MATHEMATICAL MODELS; RANDOM PROCESSES; RISK MANAGEMENT; TIME SERIES ANALYSIS;

STRUCTURAL RISK MINIMIZATION METHOD; VAPNIK-CHERVONENKIS METHOD;

LEARNING SYSTEMS;

EID: 0033904367     PISSN: 08856125     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1007602715810     Document Type: Article

References (44)

1. Arcones, M. A. & Yu, B. (1994). Central limit theorems for empirical and u-proceses of stationary mixing sequences. J. Theoretical Prob., 7(1), 47-71.
2. Barron, A.R. (1993). Universal approximation bound for superpositions of a sigmoidal function. IEEE Trans. Inf. Th., 39, 930-945.
3. Barron, A. (1994). Approximation and Estimation Bounds for Artificial Neural Networks. Machine Learning, 4, 115-133.
4. Barron, A., Birgé, L., & Massart, P. (1999). Risk Bounds for Model Selection via Penalization. Th. and Related Fields, 113(3), 301-413.
5. Barron, A. & Cover, T. (1991). Minimum Complexity Density Estimation. IEEE Trans. Inf. Theory, 37(4), 1034-1054.
6. Bartlett, P.L., Long, P.M., & Williamson, R.C. (1996). Fat-shattering and the learnability of real-valued functions. Journal of Computer and System Sciences, 52(3), 434-452.
7. Bartlett, P.L., Maiorov, V., & Meir, R. (1998). Almost linear vc dimension bounds for piecwise polynomial networks. Neural Computation, 10, 2159-2173.
8. Blum, A. (1996). On-line algorithms in machine learning. Technical Report, Carnegie Mellon University, Presented at Dagstuhl Workshop on On-Line Algorithms. http://www.cs.cmu.edu/People/avrim/Papers/survey.ps.gz.
9. Bosq, D. (1996). Nonparametric statistics for stochastic processes: Estimation and Prediction. New York: Springer Verlag.
10. Brockwell, P.J. & Davis, R.A. (1991). Time series: theory and methods. New York: Springer Verlag.
11. Campi, M.C. & Kumar, RR. (1998). Learning dynamical systems in a stationary environment. Systems and Control Letters, 34, 125-132.
12. Craig, C.C. (1993). On the Tchebycheff Inequality of Bernstein. Ann. Math. Statis., 4, 94-102.
13. Devroye, L., Györfi, L., & Lugosi, G. (1996). A probabilistic theory of pattern recognition. New York: Springer Verlag.
14. Devore, R.A. & Lorentz, G.G. (1993). Constructive approximation. New York: Springer Verlag.
15. Doukhan, P. (1994). Mixing - properties and examples. New York: Springer Verlag.
16. Feder, M. & Merhav, N. (1996). Hierarchical universal coding. IEEE Trans. Inf. Th., 42(5), 1354-1364.
17. Geman, S. & Hwang, C.R. (1982). Nonparameteric Maximum Likelihood Estimation by the Method of Sieves. Annals of Statistics, 10(2), 401-414.
18. Goldberg, RW. & Jerrum, M.R. (1995). Bounding the VC Dimension of Concept Classes Parameterized by Real Numbers. Machine Learning, 18, 131-148.
19. Grenander, U. (1981). Abstract inference. New York: John Wiley.
20. Györfi, L., Härdle, W., Sarda, P., & Vieu, P. (1989). Nonparametric curve estimation from time series. New York: Springer Verlag.
21. Haussler, D. (1992). Decision Theoretic Generalizations of the PAC Model for Neural Net and Other Learning Applications. Information and Computation, 100, 78-150.
22. Haussler, D. (1995). Sphere Packing Numbers for Subsets of the Boolean n-Cube with Bounded Vapnik-Chervonenkis Dimesnion. J. Combinatorial Theory, Series A, 69, 217-232.
23. Hoeffding, W. (1963). Probability inequalities for sums of bounded random variables. J. Amer. Statis. Assoc., 58, 13-30.
24. Karpinksi, M. & Macintyre, A. (1997). Polynomial Bounds for VC Dimension of Sigmoidal and General Pfaffian Neural Networks. Journal of Computer and System Science, 54, 169-176.
25. Lee, W.S., Bartlett, P.S., & Williamson, R.C. (1996). Efficient Agnostic learning of neural networks with bounded fan-in. IEEE Trans. Inf. Theory, 42(6), 2118-2132.
26. Lugosi, G. & Nobel, A. (1996). Adaptive Model Selection Using Empirical Complexities, preprint.
27. Lugosi, G. & Zeger, K. (1995). Nonparametric Estimation via Empirical Risk Minimization. IEEE Trans. Inf. Theory, 41(3), 677-687.
28. Lugosi, G. & Zeger, K. (1996). Concept learning using complexity regularization. IEEE Trans. Inf. Theory, 42(1), 48-54.
29. Maiorov, V.E. & Meir, R. (in press). On the near optimality of the stochastic approximation of smooth functions by neural network. Advances in Computational Mathematics.
30. Mhaskar, H. (1996). Neural Networks for Optimal Approximation of Smooth and Analytic Functions. Neural Computation, 8(1), 164-177.
31. Modha, D. & Masry, E. (1998). Memory Universal Prediction of Stationary Random Processes. IEEE Trans. Inf. Th., 44(1), 117-133.
32. Mokkadem, A. (1988). Mixing Properties of ARMA Processes. Stochastics Proc. Appl., 29, 309-315.
33. Pollard, D. (1984). Convergence of empirical processes. New York: Springer Verlag.
34. Rosenblatt, M. (1971). Markov processes: structure and asymptotic behavior. New York: Springer Verlag.
35. Stone, C.J. (1982). Optimal global rates of convergence for nonparametric estimators. Annals of Statistics, 10, 1040-1053.
36. van de Geer, S. (1987). A new approach to least-squares estimation, with applications. The Annals of Statistics, 15(2), 587-602.
37. van der Vaart, A.W. & Wellner, J.A. (1996). Weak convergence and empirical processes. New York: Springer Verlag.
38. Vapnik, V.N. (1982). Estimation of dependences based on empirical data. New York: Springer Verlag.
39. Vapnik, V. & Chervonenkis, A. (1971). On the uniform convergence of relative frequencies of events to their probabilities. Theory of Probability and its Applications, 16, 264-280.
40. Vidyasagar, M. (1996). A theory of learning and generalization. New York: Springer Verlag.
41. White, H. (1991). Some results on sieve estimation with dependent observations. In J. Powell, WA. Barnett, & G. Tau Chen (Eds.), Nonparametric and semi-parametric methods in econometrics and statistics. Cambridge University Press.
42. Yu, B. (1994). Rates of convergence for empirical processes of stationary mixing sequences. Annals of probability, 22, 94-116.
43. Yule, G.U. (1927). On a Method of Investigating Periodicities in Disturbed Series with Special Reference to Wölfer's Sunspot Numbers. Philos. Trans. Roy. Soc., A226, 267-298.
44. Zeevi, A., Meir, R., & Maiorov, V. (1998). Error bounds for functional approximation and estimation using mixtures of experts. IEEE Trans. Information Theory, 44(3), 1010-1025.