Prediction and estimation consistency of sparse multi-class penalized optimal scoring

被引：5

作者：

Gaynanova, Irina ^{[1
]}

机构：

[1] Texas A&M Univ, Dept Stat, MS 3143, College Stn, TX 77843 USA

来源：

BERNOULLI | 2020年 / 26卷 / 01期

基金：

美国国家科学基金会;

关键词：

classification; high-dimensional regression; lasso; linear discriminant analysis; ORACLE INEQUALITIES; DISCRIMINANT-ANALYSIS; VARIABLE SELECTION; MODEL SELECTION; REGRESSION; RECOVERY;

D O I：

10.3150/19-BEJ1126

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

Sparse linear discriminant analysis via penalized optimal scoring is a successful tool for classification in high-dimensional settings. While the variable selection consistency of sparse optimal scoring has been established, the corresponding prediction and estimation consistency results have been lacking. We bridge this gap by providing probabilistic bounds on out-of-sample prediction error and estimation error of multi-class penalized optimal scoring allowing for diverging number of classes.

引用

页码：286 / 322

页数：37

共 50 条

[1] Prediction and estimation consistency of sparse multi-class penalized optimal scoring (vol 26, pg 286, 2020)
Gaynanova, Irina
BERNOULLI, 2022, 28 (01) : 601 - 605
[2] Learning Optimal Fair Scoring Systems for Multi-Class Classification
Rouzot, Julien
Ferry, Julien
Huguet, Marie-Jose
2022 IEEE 34TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, ICTAI, 2022, : 197 - 204
[3] Development of sparse Bayesian multinomial generalized linear model for multi-class prediction
Madahian, Behrouz
Deng, Lih Y.
Homayouni, Ramin
BMC BIOINFORMATICS, 2014, 15
[4] Development of sparse Bayesian multinomial generalized linear model for multi-class prediction
Behrouz Madahian
Lih Y Deng
Ramin Homayouni
BMC Bioinformatics, 15 (Suppl 10)
[5] Multi-class classification of biomechanical data: A functional LDA approach based on multi-class penalized functional PLS
Aguilera-Morillo, M. Carmen
Aguilera, Ana M.
STATISTICAL MODELLING, 2020, 20 (06) : 592 - 616
[6] Multi-class classification of biomechanical data: A functional LDA approach based on multi-class penalized functional PLS
Carmen Aguilera-Morillo, M.
Aguilera, Ana M.
STATISTICAL MODELLING, 2019,
[7] Development of sparse Bayesian multinomial generalized linear model for multi-class prediction
Madahian, Behrouz
Deng, Lih Y.
Homayouni, Ramin
BMC BIOINFORMATICS, 2014, 15
[8] Multi-Class H-Consistency Bounds
Awasthi, Pranjal
Mao, Anqi
Mohri, Mehryar
Zhong, Yutao
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35, NEURIPS 2022, 2022,
[9] A Sparse Multi-class Classifier for Biomarker Screening
Liu, Tzu-Yu
Wiesel, Ami
Hero, Alfred O.
2013 IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (GLOBALSIP), 2013, : 77 - 80
[10] Commodity dynamics: A sparse multi-class approach
Barbaglia, Luca
Wilms, Ines
Croux, Christophe
ENERGY ECONOMICS, 2016, 60 : 62 - 72

← 1 2 3 4 5 →