Scalable Robust Matrix Recovery: Frank-Wolfe Meets Proximal Methods

@article{Mu2016ScalableRM,
  title={Scalable Robust Matrix Recovery: Frank-Wolfe Meets Proximal Methods},
  author={Cun Mu and Yuqian Zhang and John Wright and Donald Goldfarb},
  journal={SIAM J. Scientific Computing},
  year={2016},
  volume={38}
}
Recovering matrices from compressive and grossly corrupted observations is a fundamental problem in robust statistics, with rich applications in computer vision and machine learning. In theory, under certain conditions, this problem can be solved in polynomial time via a natural convex relaxation, known as Compressive Principal Component Pursuit (CPCP). However, many existing provably convergent algorithms for CPCP su↵er from superlinear per-iteration cost, which severely limits their… CONTINUE READING
Highly Cited
This paper has 54 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 23 extracted citations

Efficient Optimization Algorithms for Robust Principal Component Analysis and Its Variants

Proceedings of the IEEE • 2018
View 13 Excerpts
Method Support
Highly Influenced

Moving Object Detection Through Robust Matrix Completion Augmented With Objectness

IEEE Journal of Selected Topics in Signal Processing • 2018
View 1 Excerpt

54 Citations

0102030'14'15'16'17'18'19
Citations per Year
Semantic Scholar estimates that this publication has 54 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 47 references

Compressive principal component pursuit

2012 IEEE International Symposium on Information Theory Proceedings • 2012
View 15 Excerpts
Highly Influenced

A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems

SIAM J. Imaging Sciences • 2009
View 7 Excerpts
Highly Influenced

Toward Guaranteed Illumination Models for Non-convex Objects

2013 IEEE International Conference on Computer Vision • 2013
View 3 Excerpts