Online Robust PCA via Stochastic Optimization

By Jiashi Feng, Huan Xu, Shuicheng Yan. Neural Information Processing Systems, 2013

302 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/b2b9b9fa74dba55393261fb067256ed200ead01b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Robust Subspace Learning: Robust PCA, Robust Subspace Tracking, and Robust Subspace Recovery (2017, methodology): “In [47], an online algorithm was developed to solve the PCP convex program using stochastic optimization.”
Provable Dynamic Robust PCA or Robust Subspace Tracking (2017, unknown): “The other two online methods - GRASTA [15] and ORPCA [14] - also have some approach of tracking the subspace, however they still fail because they do not explicitly exploit the slow subspace change assumption.”
Distributed Robust Learning (2014, methodology): “Traditional robust learning methods generally rely on optimizing certain robust statistics [14, 16] or applying some sample trimming strategies [8, 9], whose calculations require loading all the samples into the memory or going through the data multiple times [10].”
Streaming PCA and Subspace Tracking: The Missing Data Case (2018, methodology): “algorithms can be developed along similar lines of PETRELS, where the loss function is revised to include regularization terms on the Frobenius norms of the subspace U and the weight vector wn, which we refer the readers to [26], [27].”
Decomposition into Low-rank plus Additive Matrices for Background/Foreground Separation: A Review for a Comparative Evaluation with a Large-Scale Dataset (2015, methodology): “[101] developed an online Robust PCA (OR-PCA) that processes one sample per time instance and hence its memory cost is independent of the number of samples, significantly enhancing the computation and storage efficiency.”
Dual Principal Component Pursuit (2015, methodology): “For methods from robust statistics see Huber (1981); Jolliffe (2002), for online subspace learning methods see Balzano et al. (2010); Feng et al. (2013), for regression-type methods see Wang et al. (2015), while for fast and other methods the reader is referred to the excellent literature review of…”