Robust PCA in High-dimension: A Deterministic Approach

Abstract

We consider principal component analysis for contaminated data-set in the high dimensional regime, where the dimensionality of each observation is comparable or even more than the number of observations. We propose a deterministic high-dimensional robust PCA algorithm which inherits all theoretical properties of its randomized counterpart, i.e., it is tractable, robust to contaminated points, easily kernelizable, asymptotic consistent and achieves maximal robustness -- a breakdown point of 50%. More importantly, the proposed method exhibits significantly better computational efficiency, which makes it suitable for large-scale real applications.

ICML2012

References in corpus (3)

• Robust Principal Component Analysis?
• Optimal Solutions for Sparse Principal Component Analysis
• Robust PCA via Outlier Pursuit

Cited by in corpus (6)

• An Overview of Robust Subspace Recovery
• Fast, Robust and Non-convex Subspace Recovery
• Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
• Distributed Robust Learning
• Closed-Form, Provable, and Robust PCA via Leverage Statistics and Innovation Search
• Informative Data Projections: A Framework and Two Examples