… improve the robustness to noise, we introduce a sparse error … of the original data in the
discriminant subspace, the proposed … a novel and robust sparse discriminative feature extraction …

… CONCLUSION This paper proposed a robust discriminant analysis cri… sparse version RSLDA
by considering an extra sparse regularization term. This makes our methods more robust to …

… Classical linear discriminant analysis (LDA) or Fisher’s LDA addresses the classification …
can be mapped into the most discriminative low-dimensional subspace (Fisher, 1936; Hastie et …

… Discriminative methods pursue a direct … , linear discriminant analysis (LDA) aims to find the
mapping that reduces the input dimensionality, while preserving the most class discriminatory …

… Linear discriminant analysis (LDA) is a well-known supervised method that … robust linear
discriminant analysis (GRLDA) method to tackle this disadvantage and improve the robustness. …

… efficient and robust sparse linear discriminant analysis (… L2,p-norm can bring higher
robustness and better accuracy. … , which further enhances the robustness in different scenarios. In …

… Linear discriminant analysis (LDA) is a popular dimensionality reduction technique … robust
and sparse LDA formulation dubbed RSLDA+. The key idea is introducing the mixed sparse …

… of robust linear discriminant analysis for dimensionality reduction which joints L2;1-norm on
objective function … such as multivariate linear regression, PCA and sparse coding and exploit …

… In this paper, we propose a robust linear discriminant analysis via simultaneous Ls-norm …
Our formulation is flexible, since it is shown that LDA-L2 and its robust variants can be …

… Although the strong assumptions used in this derivation of LDA are … linear model is more
robust against noise, and less likely to overfit. An alternative approach to discrimination analysis …