No Access

CONVERGENCE ANALYSIS OF COEFFICIENT-BASED REGULARIZATION UNDER MOMENT INCREMENTAL CONDITION

Department of Mathematics, Huizhou University, Huizhou, Guangdong 516007, P. R. China

and

School of Mathematics and Statistics, Guangdong University of Finance and Economics, Guangzhou, Guangdong 510320, P. R. China

Corresponding author.

Search for more papers by this author

https://doi.org/10.1142/S0219691314500088Cited by:5 (Source: Crossref)

Abstract

In this paper, we investigate coefficient-based regularized least squares regression problem in a data dependent hypothesis space. The learning algorithm is implemented with samples drawn by unbounded sampling processes and the error analysis is performed by a stepping-stone technique. A new error decomposition technique is proposed for the error analysis. The regularization parameters in our setting provide much more flexibility and adaptivity. Sharp learning rates are addressed by means of l²-empirical covering numbers under a moment hypothesis condition.

Keywords:

AMSC: 68T05, 62J02

References

N. Aronszajn, Trans. Amer. Math. Soc. 68, 337 (1950), DOI: 10.1090/S0002-9947-1950-0051437-7. Crossref, Web of Science, Google Scholar
G. Bennett, J. Amer. Stat. Assoc. 57(297), 33 (1962), DOI: 10.1080/01621459.1962.10482149. Crossref, Web of Science, Google Scholar
D. R. Chenet al., J. Mach. Learning Res. 5, 1143 (2004). Web of Science, Google Scholar
F. Cucker and D. X. Zhou , Learning theory: An approximation theory viewpoint ( Cambridge University Press , Cambridge , 2007 ) . Crossref, Google Scholar
Y. L. Feng and S. G. Lv, Comput. Math. Appl. 62(1), 506 (2011), DOI: 10.1016/j.camwa.2011.05.034. Crossref, Web of Science, Google Scholar
J. Huang, H. Chen and L. Q. Li, Int. J. Wavelets Multiresolut. Inf. Process. 10(1), (2012), DOI: 10.1142/S021969131100447X. Google Scholar
J. W. Ma, Int. J. Wavelets Multiresolut. Inf. Process. 9(1), 63 (2011), DOI: 10.1142/S0219691311003992. Link, Web of Science, Google Scholar
N. Saito and Z. H. Zhang, Int. J. Wavelets Multiresolut. Inf. Process. 8(2), 253 (2010), DOI: 10.1142/S0219691310003493. Link, Web of Science, Google Scholar
L. Shi, Appl. Comput. Harm. Anal. 34(2), 252 (2013), DOI: 10.1016/j.acha.2012.05.001. Crossref, Web of Science, Google Scholar
S. Smale and D. X. Zhou, Anal. Appl. 1(1), 17 (2003), DOI: 10.1142/S0219530503000089. Link, Web of Science, Google Scholar
S. Smale and D. X. Zhou, Constr. Approx. 26(2), 153 (2007), DOI: 10.1007/s00365-006-0659-y. Crossref, Web of Science, Google Scholar
S. Smale and D. X. Zhou, Anal. Appl. 7(1), 87 (2009), DOI: 10.1142/S0219530509001293. Link, Web of Science, Google Scholar
I. Steinwart and A. Christmann , Support Vector Machines ( Springer-Verlag , New York , 2008 ) . Google Scholar
H. W. Sun and Q. Wu, Appl. Comput. Harm. Anal. 30(1), 96 (2011), DOI: 10.1016/j.acha.2010.04.001. Crossref, Web of Science, Google Scholar
C. Wang and D. X. Zhou, J. Complexity 27(1), 55 (2011), DOI: 10.1016/j.jco.2010.10.002. Crossref, Web of Science, Google Scholar
Q. Wu and D. X. Zhou, Neural Computat. 17(5), 1160 (2005), DOI: 10.1162/0899766053491896. Crossref, Web of Science, Google Scholar
Q. Wu, Y. Ying and D. X. Zhou, Found. Comput. Math. 6(2), 171 (2005), DOI: 10.1007/s10208-004-0155-9. Crossref, Web of Science, Google Scholar
Q. Wu, Y. Ying and D. X. Zhou, J. Complexity 23(1), 108 (2007), DOI: 10.1016/j.jco.2006.06.007. Crossref, Web of Science, Google Scholar
Q. Wu and D. X. Zhou, Comput. Math. Appl. 56(11), 2896 (2008), DOI: 10.1016/j.camwa.2008.09.014. Crossref, Web of Science, Google Scholar
D. X. Zhou, IEEE Trans. Inf. Theory 49(7), 1743 (2003). Crossref, Web of Science, Google Scholar