Constructive analysis for coefficient regularization regression algorithms

JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS

卷:431

Article

Nie, Weilin¹  Wang, Cheng¹ 

[1] Huizhou Univ, Dept Math, Huizhou 516007, Guangdong, Peoples R China

关键词: Least squares regression;    Coefficient regularization;    Error decomposition;    Constructive stepping-stone function;   

DOI  :  10.1016/j.jmaa.2015.06.006

来源: Elsevier

【 摘 要 】

In this paper, we consider the least squares regression algorithm with a generalized coefficient regularization term. A novel error decomposition involving a constructive stepping-stone function is introduced. By choosing appropriate parameters for the constructive function we finally derive a satisfactory learning rate under some condition for the goal function and capacity of the hypothesis space. (C) 2015 Elsevier Inc. All rights reserved.

【 授权许可】

Free