Title | Learning rates of regression with q-norm loss and threshold |
Authors | Hu, Ting Yao, Yuan |
Affiliation | Wuhan Univ, Sch Math & Stat, Luojia Hill, Wuhan 430072, Peoples R China. Peking Univ, Sch Math Sci, Beijing 100871, Peoples R China. |
Keywords | Insensitive q-norm loss quantile regression reproducing kernel Hilbert space sparsity COVERING NUMBER |
Issue Date | 2016 |
Publisher | ANALYSIS AND APPLICATIONS |
Citation | ANALYSIS AND APPLICATIONS.2016,14(6,SI),809-827. |
Abstract | This paper studies some robust regression problems associated with the q-norm loss (q >= 1) and the epsilon-insensitive q-norm loss in the reproducing kernel Hilbert space. We establish a variance-expectation bound under a priori noise condition on the conditional distribution, which is the key technique to measure the error bound. Explicit learning rates will be given under the approximation ability assumptions on the reproducing kernel Hilbert space. |
URI | http://hdl.handle.net/20.500.11897/458610 |
ISSN | 0219-5305 |
DOI | 10.1142/S0219530516400030 |
Indexed | SCI(E) |
Appears in Collections: | 数学科学学院 |