How Correlations Influence Lasso Prediction

被引：66

作者：

Hebiri, Mohamed ^{[1
]}

Lederer, Johannes ^{[2
]}

机构：

[1] Univ Paris Est Marne La Vallee, F-77454 Champs Sur Marne, France

[2] Swiss Fed Inst Technol, CH-8006 Zurich, Switzerland

来源：

IEEE TRANSACTIONS ON INFORMATION THEORY | 2013年 / 59卷 / 03期

基金：

瑞士国家科学基金会;

关键词：

Correlations; Lars algorithm; Lasso; restricted eigenvalue; tuning parameter; OPTIMAL RATES; SELECTION;

D O I：

10.1109/TIT.2012.2227680

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

We study how correlations in the design matrix influence Lasso prediction. First, we argue that the higher the correlations, the smaller the optimal tuning parameter. This implies in particular that the standard tuning parameters, that do not depend on the design matrix, are not favorable. Furthermore, we argue that Lasso prediction works well for any degree of correlations if suitable tuning parameters are chosen. We study these two subjects theoretically as well as with simulations.

引用

页码：1846 / 1854

页数：9

共 28 条

[21] NUCLEAR-NORM PENALIZATION AND OPTIMAL RATES FOR NOISY LOW-RANK MATRIX COMPLETION [J].

Koltchinskii, Vladimir ;

Lounici, Karim ;

Tsybakov, Alexandre B. .

ANNALS OF STATISTICS, 2011, 39 (05) :2302-2329

[22] The Lasso as an l1-ball model selection procedure [J].

Massart, Pascal ;

Meynet, Caroline .

ELECTRONIC JOURNAL OF STATISTICS, 2011, 5 :669-687

[23] On the LASSO and its dual [J].

Osborne, MR ;

Presnell, B ;

Turlach, BA .

JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS, 2000, 9 (02) :319-337

[24] EXPONENTIAL SCREENING AND OPTIMAL RATES OF SPARSE ESTIMATION [J].

Rigollet, Philippe ;

Tsybakov, Alexandre .

ANNALS OF STATISTICS, 2011, 39 (02) :731-771

[25] Regression shrinkage and selection via the Lasso [J].

Tibshirani, R .

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 1996, 58 (01) :267-288

[26]

Turlach B., 2005, Proc. American Statistical Association, P2572

[27] On the conditions used to prove oracle results for the Lasso [J].

van de Geer, Sara A. ;

Buehlmann, Peter .

ELECTRONIC JOURNAL OF STATISTICS, 2009, 3 :1360-1392

[28]

van der Vaart A. W., 2000, WEAK CONVERGENCE EMP

← 1 2 3 →