Iteratively Reweighted Least Squares Algorithms for L1-Norm Principal Component Analysis

Abstract

Principal component analysis (PCA) is often used to reduce the dimension of data by selecting a few orthonormal vectors that explain most of the variance structure of the data. L1 PCA uses the L1 norm to measure error, whereas the conventional PCA uses the L2 norm. For the L1 PCA problem minimizing the fitting error of the reconstructed data, we propose an exact reweighted and an approximate algorithm based on iteratively reweighted least squares. We provide convergence analyses, and compare their performance against benchmark algorithms in the literature. The computational experiment shows that the proposed algorithms consistently perform best.

References in corpus (1)

• Optimal Algorithms for $L_1$-subspace Signal Processing

Cited by in corpus (5)

• A Simple and Fast Algorithm for L1-norm Kernel PCA
• Low Rank Approximation with Entrywise ${\ell }_1$-Norm Error
• A robust principal component analysis for outlier identification in messy microcalorimeter data
• Optimization for L1-Norm Error Fitting via Data Aggregation
• Optimal ${\ell }_1$ Column Subset Selection and a Fast PTAS for Low Rank Approximation