Concentration estimates for learning with unbounded sampling |
| |
Authors: | Zheng-Chu Guo Ding-Xuan Zhou |
| |
Institution: | 1. School of Mathematics and Computational Science, Sun Yat-sen University, Guangzhou, 510275, People’s Republic of China 2. Department of Mathematics, City University of Hong Kong, Kowloon, Hong Kong, People’s Republic of China
|
| |
Abstract: | The least-square regression problem is considered by regularization schemes in reproducing kernel Hilbert spaces. The learning algorithm is implemented with samples drawn from unbounded sampling processes. The purpose of this paper is to present concentration estimates for the error based on ?2-empirical covering numbers, which improves learning rates in the literature. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|