Asymptotically Bias-Corrected Regularized Linear Discriminant Analysis for Cost-Sensitive Binary Classification

Amin Zollanvari, Muratkhan Abdirash, Aresh Dadlani, Berdakh Abibullaev

Research output: Contribution to journalArticle

Abstract

In this letter, the theory of random matrices of increasing dimension is used to construct a form of regularized linear discriminant analysis (RLDA) that asymptotically yields the lowest overall risk with respect to the bias of the discriminant in cost-sensitive classification of two multivariate Gaussian distributions. Numerical experiments using both synthetic and real data show that even in finite-sample settings, the proposed classifier can uniformly outperform RLDA in terms of achieving a lower risk as a function of regularization parameter and misclassification costs.

Original languageEnglish
Article number8720003
Pages (from-to)1300-1304
Number of pages5
JournalIEEE Signal Processing Letters
Volume26
Issue number9
DOIs
Publication statusPublished - Sep 1 2019

Fingerprint

Binary Classification
Discriminant analysis
Discriminant Analysis
Misclassification
Gaussian distribution
Multivariate Distribution
Regularization Parameter
Costs
Random Matrices
Discriminant
Lowest
Classifiers
Classifier
Numerical Experiment
Experiments
Form

Keywords

  • bias correction
  • cost-sensitive classification
  • random matrix theory
  • Regularized linear discriminant

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Applied Mathematics

Cite this

Asymptotically Bias-Corrected Regularized Linear Discriminant Analysis for Cost-Sensitive Binary Classification. / Zollanvari, Amin; Abdirash, Muratkhan; Dadlani, Aresh; Abibullaev, Berdakh.

In: IEEE Signal Processing Letters, Vol. 26, No. 9, 8720003, 01.09.2019, p. 1300-1304.

Research output: Contribution to journalArticle

Zollanvari, Amin ; Abdirash, Muratkhan ; Dadlani, Aresh ; Abibullaev, Berdakh. / Asymptotically Bias-Corrected Regularized Linear Discriminant Analysis for Cost-Sensitive Binary Classification. In: IEEE Signal Processing Letters. 2019 ; Vol. 26, No. 9. pp. 1300-1304.
@article{73472051962f4f98a4319dc8c299367c,
title = "Asymptotically Bias-Corrected Regularized Linear Discriminant Analysis for Cost-Sensitive Binary Classification",
abstract = "In this letter, the theory of random matrices of increasing dimension is used to construct a form of regularized linear discriminant analysis (RLDA) that asymptotically yields the lowest overall risk with respect to the bias of the discriminant in cost-sensitive classification of two multivariate Gaussian distributions. Numerical experiments using both synthetic and real data show that even in finite-sample settings, the proposed classifier can uniformly outperform RLDA in terms of achieving a lower risk as a function of regularization parameter and misclassification costs.",
keywords = "bias correction, cost-sensitive classification, random matrix theory, Regularized linear discriminant",
author = "Amin Zollanvari and Muratkhan Abdirash and Aresh Dadlani and Berdakh Abibullaev",
year = "2019",
month = "9",
day = "1",
doi = "10.1109/LSP.2019.2918485",
language = "English",
volume = "26",
pages = "1300--1304",
journal = "IEEE Signal Processing Letters",
issn = "1070-9908",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "9",

}

TY - JOUR

T1 - Asymptotically Bias-Corrected Regularized Linear Discriminant Analysis for Cost-Sensitive Binary Classification

AU - Zollanvari, Amin

AU - Abdirash, Muratkhan

AU - Dadlani, Aresh

AU - Abibullaev, Berdakh

PY - 2019/9/1

Y1 - 2019/9/1

N2 - In this letter, the theory of random matrices of increasing dimension is used to construct a form of regularized linear discriminant analysis (RLDA) that asymptotically yields the lowest overall risk with respect to the bias of the discriminant in cost-sensitive classification of two multivariate Gaussian distributions. Numerical experiments using both synthetic and real data show that even in finite-sample settings, the proposed classifier can uniformly outperform RLDA in terms of achieving a lower risk as a function of regularization parameter and misclassification costs.

AB - In this letter, the theory of random matrices of increasing dimension is used to construct a form of regularized linear discriminant analysis (RLDA) that asymptotically yields the lowest overall risk with respect to the bias of the discriminant in cost-sensitive classification of two multivariate Gaussian distributions. Numerical experiments using both synthetic and real data show that even in finite-sample settings, the proposed classifier can uniformly outperform RLDA in terms of achieving a lower risk as a function of regularization parameter and misclassification costs.

KW - bias correction

KW - cost-sensitive classification

KW - random matrix theory

KW - Regularized linear discriminant

UR - http://www.scopus.com/inward/record.url?scp=85069969310&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069969310&partnerID=8YFLogxK

U2 - 10.1109/LSP.2019.2918485

DO - 10.1109/LSP.2019.2918485

M3 - Article

AN - SCOPUS:85069969310

VL - 26

SP - 1300

EP - 1304

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

SN - 1070-9908

IS - 9

M1 - 8720003

ER -