Robust Subspace Learning: Robust PCA, Robust Subspace Tracking, and Robust Subspace Recovery

Abstract

PCA is one of the most widely used dimension reduction techniques. A related easier problem is "subspace learning" or "subspace estimation". Given relatively clean data, both are easily solved via singular value decomposition (SVD). The problem of subspace learning or PCA in the presence of outliers is called robust subspace learning or robust PCA (RPCA). For long data sequences, if one tries to use a single lower dimensional subspace to represent the data, the required subspace dimension may end up being quite large. For such data, a better model is to assume that it lies in a low-dimensional subspace that can change over time, albeit gradually. The problem of tracking such data (and the subspaces) while being robust to outliers is called robust subspace tracking (RST). This article provides a magazine-style overview of the entire field of robust subspace learning and tracking. In particular solutions for three problems are discussed in detail: RPCA via sparse+low-rank matrix decomposition (S+LR), RST via S+LR, and "robust subspace recovery (RSR)". RSR assumes that an entire data vector is either an outlier or an inlier. The S+LR formulation instead assumes that outliers occur on only a few data vector indices and hence are well modeled as sparse corruptions.

To appear, IEEE Signal Processing Magazine, July 2018

References in corpus (6)

• An Overview of Robust Subspace Recovery
• Non-convex Robust PCA
• Compressive Principal Component Pursuit
• Nearly Optimal Robust Subspace Tracking
• pROST : A Smoothed Lp-norm Robust Online Subspace Tracking Method for Realtime Background Subtraction in Video
• Learning Robust Low-Rank Representations

Cited by in corpus (17)

• Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
• Static and Dynamic Robust PCA and Matrix Completion: A Review
• On Universal Features for High-Dimensional Learning and Inference
• FAST-PCA: A Fast and Exact Algorithm for Distributed Principal Component Analysis
• Graph-Embedded Subspace Support Vector Data Description
• Background Subtraction in Real Applications: Challenges, Current Models and Future Directions
• Fast Robust Subspace Tracking via PCA in Sparse Data-Dependent Noise
• On-line Non-Convex Constrained Optimization
• Unsupervised RGBD Video Object Segmentation Using GANs
• Fast and Robust LRSD-based SAR/ISAR Imaging and Decomposition
• Spectrally Constrained Optimization
• Graph Embedding with Data Uncertainty
• Summarizing the performances of a background subtraction algorithm measured on several videos
• ALPCAH: Sample-wise Heteroscedastic PCA with Tail Singular Value Regularization
• Enhancing the Spatio-Temporal Observability of Residential Loads
• Reduce the rank calculation of a high-dimensional sparse matrix based on network controllability theory
• Robust Principal Components by Casewise and Cellwise Weighting