A Bias Trick for Centered Robust Principal Component Analysis

2019/11/19 by Baokun He, Guihong Wan, He, Baokun +3
Computer Science · Engineering · Mathematics · #Advanced Statistical Methods and Models #Blind Source Separation Techniques #FOS: Computer and information sciences #Fault Detection and Control Systems #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.1911.08024

openalex publication_date 2019/11/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Outlier based Robust Principal Component Analysis (RPCA) requires centering of the non-outliers. We show a "bias trick" that automatically centers these non-outliers. Using this bias trick we obtain the first RPCA algorithm that is optimal with respect to centering.

Related

• Robust Principal Component Analysis Using Statistical Estimators
• A Fast Iterative Robust Principal Component Analysis Method
• Robust Orthogonal Complement Principal Component Analysis
• Thresholding based Efficient Outlier Robust PCA
• Robust Principal Component Analysis: A Median of Means Approach