Abstract
The least-square regression problem is considered by coefficient-based regularization schemes with ℓ1 −penalty. The learning algorithm is analyzed with samples drawn from unbounded sampling processes. The purpose of this paper is to present an elaborate concentration estimate for the algorithms by means of a novel stepping stone technique. The learning rates derived from our analysis can be achieved in a more general setting. Our refined analysis will lead to satisfactory learning rates even for non-smooth kernels.
Similar content being viewed by others
References
Aronszajn, N.: Theory of reproducing kernels. Trans. Am. Math. Soc. 68, 337–404 (1950)
Bennett, G.: Probability inequalities for the sum of independent random variables. J. Am. Stat. Assoc. 57, 33–45 (1962)
Candès, E., Romberg, J.: Sparsity and incoherence in compressive sampling. Inverse Probl. 23, 969–985 (2007)
Cucker, F., Zhou, D.X.: Learing Theory: An Approxiamtion Theory Viewpoint. Cambridge University Press (2007)
Conway, J.B.: A Course in Operator Theory. AMS (2000)
Guo, Z.C., Zhou, D.X.: Concentration estimates for learning with unbounded sampling. Adv. Comput. Math. doi:10.1007/s10444-011-9238-8
Liu, C.: Gabor-based kernel pca with fractional power polynomial models for face recognition. IEEE Trans. Pattern Anal. Mach. Intell. 26, 572–581 (2004)
Lin, H., Lin, C.: A study on sigmoid kernels for SVM and the training of non-PSD kernles by SMO-type methods. In: Technical report, Department of Computer Science and Information Engineering, National Taiwan University (2003)
Mendelson, S., Neeman, J.: Regularization in kernel learning. Ann. Stat. 38, 526–565 (2010)
Opfer, R.: Multiscale kernels. Adv. Comput. Math. 25, 357–380 (2006)
Song, G., Zhang, H.: Reproducing kernel Banach spaces with the l1 norm II: error analysis for regularized least square regression. Neural Comput. 23, 2713–2729 (2011)
Song, G., Zhang, H., Hickernell, F.J.: Reproducing kernel Banach spaces with the l1 norm. Appl. Comput. Harmon. Anal. 34, 96–116 (2013)
Steinwart, I., Scovel, C.: Fast rates for support vector machines. Lect. Notes Comput. Sci. 3559, 279–294 (2005)
Shi, L., Feng, Y.L., Zhou, D.X.: Concentration estimates for learning with ℓ1-regularizer and data dependent hypothesis spaces. Appl. Comput. Harmon. Anal. 31, 286-302 (2011)
Smale, S., Zhou, D.X.: Learning theory estimates via integral operators and their approximations. Constr. Approx. 26, 153–172 (2007)
Tibshirani, R.: Regression shrinkage and selection via the lasso. J. R. Stat. Soc. B 58, 267–288 (1996)
van der Vaart, A.W., Wellner, J.A.: Weak Convergence and Emprical Processes, Springer-Verlag, New York (1996)
De Vito, E., Caponnetto, A., Rosasco, L.: Model selection for regularized least-squares algorithm in learning theory. Found. Comput. Math. 5, 59–85 (2005)
Vapnik, V.: Statistical Learning Theory. Wiley, New York (1998)
Wahba, G.: Spline Models for Observational Data. SIAM (1990)
Wu, Q., Zhou, D.X.: SVM soft margin classifier: linear programming versus quadratic programming. Neural Comput. 15, 1397–1437 (2003)
Wu, Q., Ying, Y., Zhou, D.X.: Learning rates of least-square regularized regression. Found. Comput. Math. 6, 171–192 (2006)
Wu, Q., Zhou, D.X.: Learning with sample dependent hypothesis spaces. Comput. Math. Appl. 56, 2896–2907 (2008)
Xiao, Q.W., Zhou, D.X.: Learning by nonsymmetric kernel with data dependent spaces and ℓ1-regularizer. Taiwan. J. Math. 14, 1821–1836 (2010)
Xu, Y.S., Zhang, H.Z.: Refinable kernels. J. Mach. Learn. Res. 8, 2083–2120 (2007)
Zhang, T.: Leave-one-out bounds for kernel methods. Neural Comput. 15, 1397–1437 (2003)
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by: Lixin Shen.
The work described in this paper is supported by the National Science Foundation of China under Grand 11201079.
Rights and permissions
About this article
Cite this article
Guo, ZC., Shi, L. Learning with coefficient-based regularization and ℓ1 −penalty. Adv Comput Math 39, 493–510 (2013). https://doi.org/10.1007/s10444-012-9288-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10444-012-9288-6
Keywords
- Learning theory
- Coefficient-based regularization and ℓ1-penalty
- Unbounded sampling processes
- Concentration estimate for error analysis