Classification in high dimension using the Ledoit-Wolf shrinkage method
Loading...
Date
Authors
Lotfi, Rasoul
Shahsavani, Davood
Arashi, Mohammad
Journal Title
Journal ISSN
Volume Title
Publisher
MDPI
Abstract
Classification using linear discriminant analysis (LDA) is challenging when the number
of variables is large relative to the number of observations. Algorithms such as LDA require the
computation of the feature vector’s precision matrices. In a high-dimension setting, due to the
singularity of the covariance matrix, it is not possible to estimate the maximum likelihood estimator
of the precision matrix. In this paper, we employ the Stein-type shrinkage estimation of Ledoit and
Wolf for high-dimensional data classification. The proposed approach’s efficiency is numerically
compared to existing methods, including LDA, cross-validation, gLasso, and SVM. We use the
misclassification error criterion for comparison.
Description
Keywords
Classification, High-dimensional data, Ledoit and Wolf shrinkage method, Stein-type shrinkage, Linear discriminant analysis (LDA), Support vector machine (SVM)
Sustainable Development Goals
Citation
Lotfi, R.; Shahsavani, D.;
Arashi, M. Classification in High
Dimension Using the Ledoit–Wolf
Shrinkage Method. Mathematics 2022,
10, 4069. https://doi.org/10.3390/math10214069.