Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Matrices

Abstract

This paper has been withdrawn due to a critical error near equation (71). This error causes the entire argument of the paper to collapse. Emmanuel Candes of Stanford discovered the error, and has suggested a correct analysis, which will be reported in a separate publication.

References in corpus (4)

• A Singular Value Thresholding Algorithm for Matrix Completion
• Matrix Completion With Noise
• CoSaMP: Iterative signal recovery from incomplete and inaccurate samples
• The Power of Convex Relaxation: Near-Optimal Matrix Completion

Cited by in corpus (12)

• A Gradient Descent Algorithm on the Grassman Manifold for Matrix Completion
• Matrix Completion from Noisy Entries
• Low-Rank Structure Learning via Log-Sum Heuristic Recovery
• Augmented L1 and Nuclear-Norm Models with a Globally Linearly Convergent Algorithm
• Guaranteed Rank Minimization via Singular Value Projection
• Note on sampling without replacing from a finite collection of matrices
• Subspace-Orbit Randomized Decomposition for Low-rank Matrix Approximation
• Strongly Convex Programming for Exact Matrix Completion and Robust Principal Component Analysis
• Optimal Shrinkage of Singular Values Under Random Data Contamination
• Strongly Convex Programming for Principal Component Pursuit
• Randomized Rank-Revealing UZV Decomposition for Low-Rank Approximation of Matrices
• Anomaly detecting and ranking of the cloud computing platform by multi-view learning