Matrix completion from a few entries

Authors:
Raghunandan H. Keshavan;Sewoong Oh;Andrea Montanari
Affiliations:
EE Department, Stanford University, Stanford, CA;EE Department, Stanford University, Stanford, CA;EE and Statistics Departments, Stanford University, Stanford, CA
Venue:
ISIT'09 Proceedings of the 2009 IEEE international conference on Symposium on Information Theory - Volume 1
Year:
2009

Citing 6
Cited 11

On the second eigenvalue of random regular graphs

STOC '89 Proceedings of the twenty-first annual ACM symposium on Theory of computing
The Geometry of Algorithms with Orthogonality Constraints

SIAM Journal on Matrix Analysis and Applications
Matrices, Vector Spaces, and Information Retrieval

SIAM Review
Spectral techniques applied to sparse random graphs

Random Structures & Algorithms
Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information

IEEE Transactions on Information Theory
Compressed sensing

IEEE Transactions on Information Theory

Accurate low-rank matrix recovery from a small number of linear measurements

Allerton'09 Proceedings of the 47th annual Allerton conference on Communication, control, and computing
The power of convex relaxation: near-optimal matrix completion

IEEE Transactions on Information Theory
Spatiotemporal imaging with partially separable functions: a matrix recovery approach

ISBI'10 Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to Macro
ADMiRA: atomic decomposition for minimum rank approximation

IEEE Transactions on Information Theory
Inferring invisible traffic

Proceedings of the 6th International COnference
Uniqueness of Low-Rank Matrix Completion by Rigidity Theory

SIAM Journal on Matrix Analysis and Applications
Transactional Database Transformation and Its Application in Prioritizing Human Disease Genes

IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
Short paper: location privacy: user behavior in the field

Proceedings of the second ACM workshop on Security and privacy in smartphones and mobile devices
On traffic matrix completion in the internet

Proceedings of the 2012 ACM conference on Internet measurement conference
DMFSGD: a decentralized matrix factorization algorithm for network distance prediction

IEEE/ACM Transactions on Networking (TON)
Spectrum inpainting: a new framework for spectrum status determination in large cognitive radio networks

Wireless Networks

Quantified Score

Hi-index	0.12

Visualization

Abstract

Let M be an nα × n matrix of rank r ≪ n, and assume that a uniformly random subset E of its entries is observed. We describe an efficient algorithm that reconstructs M from |E| = O(r n) observed entries with relative root mean square error RMSE ≤ C(α) (nr/|E|)1/2. Further, if r = O(1) and M is sufficiently unstructured, then it can be reconstructed exactly from |E| = O(n log n) entries. This settles (in the case of bounded rank) a question left open by Candès and Recht and improves over the guarantees for their reconstruction algorithm. The complexity of our algorithm is O(|E|r log n), which opens the way to its use for massive data sets. In the process of proving these statements, we obtain a generalization of a celebrated result by Friedman-Kahn-Szemerédi and Feige-Ofek on the spectrum of sparse random matrices.