LDA via L1-PCA of Whitened Data - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Signal Processing Année : 2020

LDA via L1-PCA of Whitened Data

Résumé

Principal component analysis (PCA) and Fisher's linear discriminant analysis (LDA) are widespread techniques in data analysis and pattern recognition. Recently, the L1-norm has been proposed as an alternative criterion to classical L2-norm in PCA, drawing considerable research interest on account of its increased robustness to outliers. The present work proves that, combined with a whitening preprocessing step, L1-PCA can perform LDA in an unsupervised manner, i.e., sparing the need for labelled data. Rigorous proof is given in the case of data drawn from a mixture of Gaussians. A number of numerical experiments on synthetic as well as real data confirm the theoretical findings.

Dates et versions

hal-02486881 , version 1 (21-02-2020)

Identifiants

Citer

Rubén Martín-Clemente, Vicente Zarzoso. LDA via L1-PCA of Whitened Data. IEEE Transactions on Signal Processing, 2020, 68, pp.225-240. ⟨10.1109/TSP.2019.2955860⟩. ⟨hal-02486881⟩
59 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More