×

A note on application of integral operator in learning theory. (English) Zbl 1165.68059

Summary: By the aid of the properties of the square root of positive operators we refine the consistency analysis of regularized least square regression in a reproducing kernel Hilbert space. Sharper error bounds and faster learning rates are obtained when the sampling sequence satisfies a strongly mixing condition.

MSC:

68T05 Learning and adaptive systems in artificial intelligence
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Aronszajn, N., Theory of reproducing kernels, Trans. Amer. Math. Soc., 68, 337-404 (1950) · Zbl 0037.20701
[2] Athreya, K. B.; Pantula, S. G., Mixing properties of Harris chains and autoregressive processes, J. Appl. Probab., 23, 880-892 (1986) · Zbl 0623.60087
[3] Bousquet, O.; Elisseeff, A., Stability and generalization, J. Mach. Learn. Res., 2, 499-526 (2002) · Zbl 1007.68083
[4] Carrasco, M.; Chen, X., Mixing and moment properties of various GARCH and stochastic volatility models, Econom. Theory, 18, 17-39 (2002) · Zbl 1181.62125
[5] Cucker, F.; Zhou, D. X., Learning Theory: An Approximation Theory Viewpoint (2007), Cambridge University Press: Cambridge University Press Cambridge, UK · Zbl 1274.41001
[6] Douglas, R. G., Banach Algebra Techniques in Operator Theory (1998), Springer: Springer New York · Zbl 0920.47001
[7] Evgeniou, T.; Pontil, M.; Poggio, T., Regularization networks and support vector machines, Adv. Comput. Math., 13, 1-50 (2000) · Zbl 0939.68098
[8] Gouriéroux, C., ARCH Model and Financial Application (1997), Springer: Springer New York
[9] Lowner, K., Über monotone Matrixfunktionen, Math. Z., 38, 177-216 (1934) · JFM 60.0055.01
[10] Modha, D. S., Minimum complexity regression estimation with weakly dependent observations, IEEE Trans. Inform. Theory, 42, 2133-2145 (1996) · Zbl 0868.62015
[11] Pedersen, G. K., Some operator monotone functions, Proc. Amer. Math. Soc., 36, 309-310 (1972) · Zbl 0256.47019
[12] Smale, S.; Zhou, D. X., Estimating the approximation error in learning theory, Anal. Appl., 1, 17C41 (2003)
[13] Smale, S.; Zhou, D. X., Shannon sampling II: Connections to learning theory, Appl. Comput. Harmon. Anal., 19, 285-302 (2005) · Zbl 1107.94008
[14] Smale, S.; Zhou, D. X., Learning theory estimates via integral operators and their approximations, Constr. Approx., 26, 153-172 (2007) · Zbl 1127.68088
[15] S. Smale, D.X. Zhou, Online learning with Markov sampling, Anal. Appl., in press; S. Smale, D.X. Zhou, Online learning with Markov sampling, Anal. Appl., in press · Zbl 1170.68022
[16] H.W. Sun, Q. Wu, Regularized least square regression with dependent samples, Adv. Comput. Math. (2008), doi:10.1007/s10444-008-9099-y; H.W. Sun, Q. Wu, Regularized least square regression with dependent samples, Adv. Comput. Math. (2008), doi:10.1007/s10444-008-9099-y · Zbl 1191.68535
[17] Vapnik, V. N., Statistical Learning Theory (1998), Wiley: Wiley New York · Zbl 0935.62007
[18] White, H., Connectionist nonparametric regression: Multilayer feedforward networks can learn arbitrary mappings, Neural Networks, 3, 535-549 (1990)
[19] Wu, Q.; Ying, Y. M.; Zhou, D. X., Learning rates of least-square regularized regression, Found. Comput. Math., 6, 171-192 (2006) · Zbl 1100.68100
[20] Xu, Y. L.; Chen, D. R., Learning rates of regularized regression for exponentially strongly mixing sequence, J. Statist. Plann., 138, 7, 2180-2189 (2008) · Zbl 1134.62050
[21] Zhang, T., Leave-one-out bounds for kernel methods, Neural Comput., 15, 1397-1437 (2003) · Zbl 1085.68144
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.