A consistent algorithm to solve Lasso, elastic-net and Tikhonov regularization

被引：6
作者：
De Vito, Ernesto [1 ]
Umanita, Veronica [1 ]
Villa, Silvia [1 ]
机构：
[1] Univ Genoa, Dipartimento Matemat, I-16146 Genoa, Italy
来源：
JOURNAL OF COMPLEXITY | 2011年 / 27卷 / 02期
关键词：
Learning theory; Regularization; Sparsity; Consistent estimator; SELECTION; MODELS;
D O I：
10.1016/j.jco.2011.01.003
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
In the framework of supervised learning, we prove that the iterative algorithm introduced in Umanita and Villa (2010)[22] allows us to estimate in a consistent way the relevant features of the regression function under the a priori assumption that it admits a sparse representation on a fixed dictionary. (C) 2011 Elsevier Inc. All rights reserved.
引用
收藏
页码：188 / 200
页数：13
相关论文
共 26 条
[1]  
[Anonymous], 1995, THEORY STAT
[2]   Honest variable selection in linear and logistic regression models via l1 and l1 + l2 penalization [J].
Bunea, Florentina .
ELECTRONIC JOURNAL OF STATISTICS, 2008, 2 :1153-1194
[3]  
Candes E, 2007, ANN STAT, V35, P2313, DOI 10.1214/009053606000001523
[4]   Atomic decomposition by basis pursuit [J].
Chen, SSB ;
Donoho, DL ;
Saunders, MA .
SIAM JOURNAL ON SCIENTIFIC COMPUTING, 1998, 20 (01) :33-61
[5]   Signal recovery by proximal forward-backward splitting [J].
Combettes, PL ;
Wajs, VR .
MULTISCALE MODELING & SIMULATION, 2005, 4 (04) :1168-1200
[6]   Best choices for regularization parameters in learning theory: On the bias-variance problem [J].
Cucker, F ;
Smale, S .
FOUNDATIONS OF COMPUTATIONAL MATHEMATICS, 2002, 2 (04) :413-428
[7]  
Cucker F, 2002, B AM MATH SOC, V39, P1
[8]   An iterative thresholding algorithm for linear inverse problems with a sparsity constraint [J].
Daubechies, I ;
Defrise, M ;
De Mol, C .
COMMUNICATIONS ON PURE AND APPLIED MATHEMATICS, 2004, 57 (11) :1413-1457
[9]   Elastic-net regularization in learning theory [J].
De Mol, Christine ;
De Vito, Ernesto ;
Rosasco, Lorenzo .
JOURNAL OF COMPLEXITY, 2009, 25 (02) :201-230
[10]   Adaptive Kernel Methods Using the Balancing Principle [J].
De Vito, E. ;
Pereverzyev, S. ;
Rosasco, L. .
FOUNDATIONS OF COMPUTATIONAL MATHEMATICS, 2010, 10 (04) :455-479
123