A Pure L1-norm Principal Component Analysis.

ABSTRACT: The L₁ norm has been applied in numerous variations of principal component analysis (PCA). L₁-norm PCA is an attractive alternative to traditional L₂-based PCA because it can impart robustness in the presence of outliers and is indicated for models where standard Gaussian assumptions about the noise may not apply. Of all the previously-proposed PCA schemes that recast PCA as an optimization problem involving the L₁ norm, none provide globally optimal solutions in polynomial time. This paper proposes an L₁-norm PCA procedure based on the efficient calculation of the optimal solution of the L₁-norm best-fit hyperplane problem. We present a procedure called L₁-PCA* bas

SUBMITTER: Brooks J 

PROVIDER: S-EPMC3746759 | biostudies-literature | 2013 May

REPOSITORIES: biostudies-literature