On the dimension effect of regularized linear discriminant analysis

On the dimension effect of regularized linear discriminant analysis
复制标题

正则化线性判别分析的量纲效应

DOI:
10.1214/18-ejs1469
复制
发表时间:
2017-10
影响因子:
1.1
通讯作者:
Jiang Binyan
Jiang Binyan
中科院分区:
数学3区
文献类型:
--
作者:
Wang Cheng;Jiang Binyan

文献摘要

参考文献

相似文献

本文研究了线性判别分析(LDA)和正则化线性判别分析(RLDA)分类器对于大维数据的维度效应,其中观察维度$p$与样本大小$n$具有相同的量级。更具体地说,基于 Wishart 分布的性质和随机矩阵理论的最新结果,我们分别推导了 LDA 和 RLDA 渐近误分类误差的显式表达式,从中我们深入了解维度如何影响分类性能以及在何种意义上影响分类性能。受这些结果的启发,我们提出通过纠正维度效应带来的偏差来调整分类器。
This paper studies the dimension effect of the linear discriminant analysis (LDA) and the regularized linear discriminant analysis (RLDA) classifiers for large dimensional data where the observation dimension $p$ is of the same order as the sample size $n$. More specifically, built on properties of the Wishart distribution and recent results in random matrix theory, we derive explicit expressions for the asymptotic misclassification errors of LDA and RLDA respectively, from which we gain insights of how dimension affects the performance of classification and in what sense. Motivated by these results, we propose adjusted classifiers by correcting the bias brought by the dimension effect.
DOI: 10.1198/tech.2004.s754
发表时间: 2004
期刊: Technometrics
影响因子: 2.5
作者:
A. Vogler
通讯作者: A. Vogler
DOI: 10.1007/s10959-011-0340-0
发表时间: 2010-04
影响因子: 0.8
作者:
Sho Matsumoto
通讯作者: Sho Matsumoto
DOI: 10.1080/00401706.1986.10488123
发表时间: 1986-05
期刊: Technometrics
影响因子: 2.5
作者:
J. Schmee
通讯作者: J. Schmee
DOI: 10.1214/009117906000001079
发表时间: 2007-07-01
影响因子: 2.3
作者:
Bai, Z. D.;Miao, B. Q.;Pan, G. M.
通讯作者: Pan, G. M.