Abstract
This paper considers the regularized learning algorithm associated with the least-square loss and reproducing kernel Hilbert spaces. The target is the error analysis for the regression problem in learning theory. A novel regularization approach is presented, which yields satisfactory learning rates. The rates depend on the approximation property and on the capacity of the reproducing kernel Hilbert space measured by covering numbers. When the kernel is C∞ and the regression function lies in the corresponding reproducing kernel Hilbert space, the rate is mζ with ζ arbitrarily close to 1, regardless of the variance of the bounded probability distribution.
Similar content being viewed by others
Author information
Authors and Affiliations
Corresponding authors
Rights and permissions
About this article
Cite this article
Wu, Q., Ying, Y. & Zhou, DX. Learning Rates of Least-Square Regularized Regression. Found Comput Math 6, 171–192 (2006). https://doi.org/10.1007/s10208-004-0155-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10208-004-0155-9