Constructive analysis for coefficient regularization regression algorithms
Constructive analysis for coefficient regularization regression algorithms
复制标题
系数正则化回归算法的建设性分析
DOI:
10.1016/j.jmaa.2015.06.006
复制
发表时间:
2015-11-15
影响因子:
1.3
通讯作者:
Wang, Cheng
中科院分区:
文献类型:
--
作者:
Nie, Weilin;Wang, Cheng
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.