On the sign recovery by least absolute shrinkage and selection operator, thresholded least absolute shrinkage and selection operator, and thresholded basis pursuit denoising

Patrick J.C. Tardivel; Ma?gorzata Bogdan

首页> 外文期刊>Scandinavian journal of statistics: Theory and applications >On the sign recovery by least absolute shrinkage and selection operator, thresholded least absolute shrinkage and selection operator, and thresholded basis pursuit denoising

【24h】

On the sign recovery by least absolute shrinkage and selection operator, thresholded least absolute shrinkage and selection operator, and thresholded basis pursuit denoising

机译：On the sign recovery by least absolute shrinkage and selection operator, thresholded least absolute shrinkage and selection operator, and thresholded basis pursuit denoising

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相关主题

摘要

Abstract Basis pursuit (BP), basis pursuit deNoising (BPDN), and least absolute shrinkage and selection operator (LASSO) are popular methods for identifying important predictors in the high‐dimensional linear regression model Y=Xβ+ε. By definition, when ε=0, BP uniquely recovers β when Xβ=Xb and β≠b implies ‖b‖1>‖β‖1 (identifiability condition). Furthermore, LASSO can recover the sign of β only under a much stronger irrepresentability condition. Meanwhile, it is known that the model selection properties of LASSO can be improved by hard thresholding its estimates. This article supports these findings by proving that thresholded LASSO, thresholded BPDN, and thresholded BP recover the sign of β in both the noisy and noiseless cases if and only if β is identifiable and large enough. In particular, if X has iid Gaussian entries and the number of predictors grows linearly with the sample size, then these thresholded estimators can recover the sign of β when the signal sparsity is asymptotically below the Donoho–Tanner transition curve. This is in contrast to the regular LASSO, which asymptotically, recovers the sign of β only when the signal sparsity tends to 0. Numerical experiments show that the identifiability condition, unlike the irrepresentability condition, does not seem to be affected by the structure of the correlations in the X matrix.

著录项

来源
《Scandinavian journal of statistics: Theory and applications》 |2022年第4期|218-250|共33页
作者
Patrick J.C. Tardivel; Ma?gorzata Bogdan;
展开▼
作者单位

University of Wroc?aw;

University of Wroc?aw||Lund University;

展开▼
收录信息
原文格式 PDF
正文语种英语
中图分类
关键词
Active set estimation; Basis pursuit; Identifiability condition; Irrepresentability condition; Lasso; Multiple regression; Sign estimation; Sparsity;

On the sign recovery by least absolute shrinkage and selection operator, thresholded least absolute shrinkage and selection operator, and thresholded basis pursuit denoising

摘要

著录项

相关主题

期刊订阅