No Access

Application of integral operator for vector-valued regression learning

School of Mathematical Science, University of Jinan, Shandong Provincial Key Laboratory of Network Based Intelligent Computing, Jinan 250022, P. R. China

Search for more papers by this author

and

Hongwei Sun

School of Mathematical Science, University of Jinan, Shandong Provincial Key Laboratory of Network Based Intelligent Computing, Jinan 250022, P. R. China

E-mail Address: ss_sunhw@ujn.edu.cn

Corresponding author.

Search for more papers by this author

https://doi.org/10.1142/S0219691315500472Cited by:3 (Source: Crossref)

Abstract

In this paper, the regression learning algorithm with vector-valued RKHS is studied. We motivate the need for extending learning theory of scalar-valued functions and analze the learning performance. In this setting, the output data are from a Hilbert space $Y$ $Y$ , the associated RKHS consists of functions with values lie in $Y$ $Y$ . By providing mathematical aspects of vector-valued integral operator $L_{K}$ $L_{K}$ , the capacity independent error bounds and learning rates are derived by means of the integral operator technique.

Keywords:

AMSC: 68T05, 68P05

References

1. N. Alon, S. Ben-David, N. Cesa-Bianchi and D. Haussler, Scale-sensitive dimesion, uniform convergence and learnability, J. Assoc. Comput. Mach. 44 (1997) 615–631. Web of Science, Google Scholar
2. R. K. Ando and T. Zhang, A framework for learning predictive structures from multiple tasks and unlabeled data, Technical Report RC23462, IBM T. J. Watson Research center (2004). Google Scholar
3. P. L. Bartlett and S. Mendelson, Rademacher and Gaussian complexities: Risk bounds and structural results, J. Mach. Learn. Res. 3 (2002) 463–482. Google Scholar
4. J. Baxter, A Bayesian/information theoretic model of learning to learn via multiple task sampling, Mach. Learn. 28 (1997) 7–39. Web of Science, Google Scholar
5. J. Baxter, A model for inductive bias learning, J. Artif. Int. Res. 12 (2000) 149–198. Web of Science, Google Scholar
6. O. Bousquet and A. Elisseeff, Stability and generalization, J. Mach. Learn. Res. 2 (2002) 499–526. Web of Science, Google Scholar
7. F. Cucker and S. Smale, On the mathematical foundations of learning, Bullet. Amer. Math. Soc. 39 (2001) 1–49. Web of Science, Google Scholar
8. T. Evgeniou and M. Pontil, Regularized multi-task learning, in Proc. of the 10th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining Seattle, USA (2004), pp. 109–117. Google Scholar
9. T. Evgeniou, M. Pontil and T. Poggio, Regularization networks and support vector machines, Adv. Comput. Math. 13 (2000) 1–50. Web of Science, Google Scholar
10. T. Jebara, Multi-task feature and kernel selection for SVMs, in Int. Conf. on Marchine Learning, ICML, July (2004). Google Scholar
11. S. Liu, P. Chen and K. Q. Li, Multiple sub-hyper-spheres support vector machine for multi-class classification, Int. J. Wavelets, Multiresolut. Inf. Process. 12(3) (2014) 15 pp., doi: 10.1142/S0219691314500350. Google Scholar
12. C. A. Micchelli and M. Pontil, On learning vector-valued functions, Neural Comput. 17(1) 2005 177–204. Web of Science, Google Scholar
13. S. Smale and D. X. Zhou, Shannon sampling II. connections to learning theory, Appl. Comput. Harmon. Anal. 19 (2006) 285–302. Google Scholar
14. S. Smale and D. X. Zhou, Learning theory estimates via integral operators and their approximations, Constr. Approx. 26 (2007) 153–172. Google Scholar
15. H. W. Sun and P. Liu, Regularized least square algorithm with two kernels, Int. J. Wavelets, Multiresolut. Inf. Process. 10(5) (2012), Article ID: 1250043, 14 pp. Link, Web of Science, Google Scholar
16. H. W. Sun and Q. Wu, A note on application of integral operator in learning theory, Appl. Comput. Harmon. Anal. 26 (2009) 416–421. Google Scholar
17. S. Thrun and L. Pratt, Learning to Learn (Kluwer Academic Publishers, 1997). Google Scholar
18. E. D. Vitoa, V. Umanita and S. Villa, An extension of Mercer theorem to matrix-valued measurable kernels, Appl. Comput. Harmon. Anal. 34 (2013) 339–351. Google Scholar
19. C. Wang and Z. C. Guo, ERM learning algorithm for multi-class classification, Appl. Anal. 91 (2012) 1339–1349. Google Scholar
20. Q. Wu, Y. M. Ying and D. X. Zhou, Learning rates of least-square regularized regression, Found. Comput. Math. 6 (2006) 171–192. Google Scholar
21. T. Zhang, Leave-one-out bounds for kernel methods, Neural Comput. 15(6) (2003) 1397–1437. Web of Science, Google Scholar