L1/2regularization

被引：0
作者：
XU ZongBen ZHANG Hai WANG Yao CHANG XiangYu LIANG Yong Institute of Information and System Science Xian Jiaotong University Xian China Department of Mathematics Northwest University Xian China University of Science and Technology Macau China [1 ,1 ,2 ,1 ,1 ,3 ,1 ,710049 ,2 ,710069 ,3 ,999078 ]
机构：
来源：
ScienceChina(InformationSciences) | 2010年 / 53卷 / 06期
关键词：
machine learning; variable selection; regularizer; compressed sensing;
D O I：
暂无
中图分类号：
TP181 [自动推理、机器学习];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper we propose an L1 /2 regularizer which has a nonconvex penalty.The L 1/2 regularizer is shown to have many promising properties such as unbiasedness, sparsity and oracle properties.A reweighed iterative algorithm is proposed so that the solution of the L 1/2 regularizer can be solved through transforming it into the solution of a series of L 1 regularizers.The solution of the L 1/2 regularizer is more sparse than that of the L 1 regularizer, while solving the L 1/2 regularizer is much simpler than solving the L 0 regularizer.The experiments show that the L 1/2 regularizer is very useful and efficient, and can be taken as a representative of the Lp(0 < p < 1) regularizer.
引用
收藏
页码：1159 / 1169
页数：11
相关论文
共 8 条
[1]  
Enhancing Sparsity by Reweighted ? 1 Minimization[J] . Emmanuel J. Candès,Michael B. Wakin,Stephen P. Boyd.Journal of Fourier Analysis and Applications . 2008 (5)
[2]  
The Dantzig Selector: Statistical Estimation When p Is Much Larger than n[J] . Emmanuel Candes,Terence Tao.The Annals of Statistics . 2007 (6)
[3]   Piecewise linear regularized solution paths [J].
Rosset, Saharon ;
Zhu, Ji .
ANNALS OF STATISTICS, 2007, 35 (03) :1012-1030
[4]   Nonconcave penalized likelihood with a diverging number of parameters [J].
Fan, JQ ;
Peng, H .
ANNALS OF STATISTICS, 2004, 32 (03) :928-961
[5]  
Least Angle Regression[J] . Bradley Efron,Trevor Hastie,Iain Johnstone,Robert Tibshirani.The Annals of Statistics . 2004 (2)
[6]   Atomic decomposition by basis pursuit [J].
Chen, SSB ;
Donoho, DL ;
Saunders, MA .
SIAM REVIEW, 2001, 43 (01) :129-159
[7]   Asymptotics for Lasso-type estimators [J].
Knight, K ;
Fu, WJ .
ANNALS OF STATISTICS, 2000, 28 (05) :1356-1378
[8]  
DC Programming: Overview[J] . R. Horst,N. V. Thoai.Journal of Optimization Theory and Applications . 1999 (1)
1