Aggregation and sparsity via l1 penalized least squares

被引：39

作者：

Bunea, Florentina ^{[1
]}

Tsybakov, Alexandre B.

Wegkamp, Marten H.

机构：

[1] Florida State Univ, Dept Stat, Tallahassee, FL 32306 USA

[2] Univ Paris 06, Lab Probabilites & Modeles Aleatoires, F-75252 Paris 05, France

[3] Inst Informat Transmiss Problems, Moscow, Russia

来源：

LEARNING THEORY, PROCEEDINGS | 2006年 / 4005卷

关键词：

D O I：

10.1007/11776420_29

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper shows that near optimal rates of aggregation and adaptation to unknown sparsity can be simultaneously achieved via, penalized least squares in a nonparametric regression setting. The main tool is a novel oracle inequality on the sum between the empirical squared loss of the penalized least squares estimate and a term reflecting the sparsity of the unknown regression function.

引用

页码：379 / 391

页数：13

共 50 条

[1] DISCRIMINANT AND SPARSITY BASED LEAST SQUARES REGRESSION WITH l1 REGULARIZATION FOR FEATURE REPRESENTATION
Zhao, Shuping
Zhang, Bob
Li, Shuyi
[J]. 2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 1504 - 1508
[2] Combined l1 and Greedy l0 Penalized Least Squares for Linear Model Selection
Pokarowski, Piotr
Mielniczuk, Jan
[J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2015, 16 : 961 - 992
[3] A Multilevel Iterated-Shrinkage Approach to l1 Penalized Least-Squares Minimization
Treister, Eran
Yavneh, Irad
[J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2012, 60 (12) : 6319 - 6329
[4] Improved Convergence for l∞ and l1 Regression via Iteratively Reweighted Least Squares
Ene, Alina
Vladu, Adrian
[J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 97, 2019, 97
[5] On denoising via penalized least-squares rules
Gudmundson, Erik
Stoica, Petre
[J]. 2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12, 2008, : 3705 - 3708
[6] Least-squares RTM with L1 norm regularisation
Wu, Di
Yao, Gang
Cao, Jingjie
Wang, Yanghua
[J]. JOURNAL OF GEOPHYSICS AND ENGINEERING, 2016, 13 (05) : 666 - 673
[7] Variable selection in spatial regression via penalized least squares
Wang, Haonan
Zhu, Jun
[J]. CANADIAN JOURNAL OF STATISTICS-REVUE CANADIENNE DE STATISTIQUE, 2009, 37 (04): : 607 - 624
[8] Density Estimation by Total Variation Penalized Likelihood Driven by the Sparsity l1 Information Criterion
Sardy, Sylvain
Tseng, Paul
[J]. SCANDINAVIAN JOURNAL OF STATISTICS, 2010, 37 (02) : 321 - 337
[9] A recursive least squares algorithm with l1 regularization for sparse representation
Liu, Di
Baldi, Simone
Liu, Quan
Yu, Wenwu
[J]. SCIENCE CHINA-INFORMATION SCIENCES, 2023, 66 (02)
[10] L1 least squares for sparse high-dimensional LDA
Li, Yanfang
Jia, Jinzhu
[J]. ELECTRONIC JOURNAL OF STATISTICS, 2017, 11 (01): : 2499 - 2518

← 1 2 3 4 5 →