您的位置:首页  > 论文页面

超高维可加模型下的特征筛选

发表时间:2015-07-15  浏览量:2122  下载量:954
全部作者: 井海银,刘朝林,张志民
作者单位: 重庆大学数学与统计学院
摘 要: 提出以核函数为基础,通过局部线性近似估计计算出估计值,并用于超高维可加模型的特征筛选方法。研究得出在一定条件下,该方法拥有安全筛选性质,并给出了其证明过程。通过实例模拟对所提方法作进一步说明,模拟结果表明:在一定样本数和较大维数条件下,所提方法拥有良好的筛选结果。
关 键 词: 数理统计学;特征筛选;超高维可加模型;局部线性近似
Title: Feature screening for ultra-high-dimensional additive models
Author: JING Haiyin, LIU Chaolin, ZHANG Zhimin
Organization: College of Mathematics and Statistics, Chongqing University
Abstract: This paper proposes feature screening method in the ultra-high-dimensional additive models based on Kernel method. In ultra-high-dimensional additive models, the proposed methods get good screening results. Under some mild technical conditions, the sure screening property is valid for the proposed method. The simulation results indicate that the proposed procedure works well with moderate sample size and large dimension.
Key words: mathematical statistics; feature screening; ultra-high-dimensional additive models; local linear approximate
发表期数: 2015年7月第13期
引用格式: 井海银,刘朝林,张志民. 超高维可加模型下的特征筛选[J]. 中国科技论文在线精品论文,2015,8(13):1351-1366.
 
2 评论数 0
暂无评论
友情链接