Corpus ID: 2090797

Nearly Optimal Robust Matrix Completion

@article{Cherapanamjeri2017NearlyOR,
  title={Nearly Optimal Robust Matrix Completion},
  author={Yeshwanth Cherapanamjeri and Kartik Gupta and Prateek Jain},
  journal={ArXiv},
  year={2017},
  volume={abs/1606.07315}
}
In this paper, we consider the problem of Robust Matrix Completion (RMC) where the goal is to recover a low-rank matrix by observing a small number of its entries out of which a few can be arbitrarily corrupted. We propose a simple projected gradient descent method to estimate the low-rank matrix that alternately performs a projected gradient descent step and cleans up a few of the corrupted entries using hard-thresholding. Our algorithm solves RMC using nearly optimal number of observations as… Expand
63 Citations
Provable Memory-efficient Online Robust Matrix Completion
  • 4
A Nonconvex Free Lunch for Low-Rank plus Sparse Matrix Recovery
  • 10
  • Highly Influenced
Fast Algorithms for Robust PCA via Gradient Descent
  • 183
  • PDF
Correction of Corrupted Columns Through Fast Robust Hankel Matrix Completion
  • Shuai Zhang, M. Wang
  • Computer Science
  • IEEE Transactions on Signal Processing
  • 2019
  • 8
  • Highly Influenced
  • PDF
Robust Low-Rank Matrix Estimation
  • 20
  • PDF
Solving the Robust Matrix Completion Problem via a System of Nonlinear Equations
  • 1
  • PDF
Robust Matrix Completion via Robust Gradient Descent
  • PDF
A Unified Framework for Low-Rank plus Sparse Matrix Recovery
  • 9
  • Highly Influenced
  • PDF
New Results for Provable Dynamic Robust PCA
  • 3
  • Highly Influenced
A Unified Framework for Nonconvex Low-Rank plus Sparse Matrix Recovery
  • 18
  • Highly Influenced
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 21 REFERENCES
Robust matrix completion
  • 73
  • PDF
Fast Exact Matrix Completion with Finite Samples
  • 70
  • PDF
Computational Limits for Matrix Completion
  • 39
  • PDF
Fast Algorithms for Robust PCA via Gradient Descent
  • 183
  • Highly Influential
  • PDF
Guaranteed Rank Minimization via Singular Value Projection
  • 448
  • PDF
Guaranteed Matrix Completion via Nonconvex Factorization
  • Ruoyu Sun, Z. Luo
  • Computer Science
  • 2015 IEEE 56th Annual Symposium on Foundations of Computer Science
  • 2015
  • 321
  • PDF
Low-Rank Matrix Recovery From Errors and Erasures
  • 128
  • PDF
Low-Rank and Sparse Structure Pursuit via Alternating Minimization
  • 55
  • PDF
Robust Matrix Decomposition With Sparse Corruptions
  • 199
  • PDF
A Simpler Approach to Matrix Completion
  • B. Recht
  • Mathematics, Computer Science
  • J. Mach. Learn. Res.
  • 2011
  • 795
  • PDF
...
1
2
3
...