Estimation of (near) low-rank matrices with noise and high-dimensional scaling

@inproceedings{Negahban2010EstimationO,
title={Estimation of (near) low-rank matrices with noise and high-dimensional scaling},
author={Sahand N. Negahban and M. Wainwright},
booktitle={ICML},
year={2010}
}
• Published in ICML 2010
• Mathematics, Computer Science
We study an instance of high-dimensional statistical inference in which the goal is to use N noisy observations to estimate a matrix Θ+ ∈ ℝk×p that is assumed to be either exactly low rank, or "near" low-rank, meaning that it can be well-approximated by a matrix with low rank. We consider an M-estimator based on regularization by the trace or nuclear norm over matrices, and analyze its performance under high-dimensional scaling. We provide non-asymptotic bounds on the Frobenius norm error that… Expand
432 Citations
ROP: Matrix Recovery via Rank-One Projections
• Mathematics, Computer Science
• ArXiv
• 2013
• 106
• PDF
On Low-rank Trace Regression under General Sampling Distribution
• Computer Science, Mathematics
• ArXiv
• 2019
• 3
• Highly Influenced
• PDF
Confidence Region of Singular Subspaces for Low-Rank Matrix Regression
• Dong Xia
• Mathematics, Computer Science
• IEEE Transactions on Information Theory
• 2019
• 3
• Highly Influenced
Robust reduced-rank regression
• Mathematics, Medicine
• Biometrika
• 2017
• 23
• PDF

References

SHOWING 1-10 OF 97 REFERENCES
Restricted strong convexity and weighted matrix completion: Optimal bounds with noise
• Mathematics, Computer Science
• J. Mach. Learn. Res.
• 2012
• 381
• PDF
High-dimensional analysis of semidefinite relaxations for sparse principal components
• Mathematics, Computer Science
• 2008 IEEE International Symposium on Information Theory
• 2008
• 239
• PDF
Spectral Regularization Algorithms for Learning Large Incomplete Matrices
• Mathematics, Computer Science
• J. Mach. Learn. Res.
• 2010
• 868
• PDF
Union support recovery in high-dimensional multivariate regression
• Computer Science, Mathematics
• 2008 46th Annual Allerton Conference on Communication, Control, and Computing
• 2008
• 70
• PDF