2018

Signal-plus-noise matrix models: eigenvector deviations and fluctuations

Cape, Joshua, Tang, Minh, Priebe, Carey E.

Understand

Estimating eigenvectors and low-dimensional subspaces is of central importance for numerous problems in statistics, computer science, and applied mathematics.

This paper characterizes the behavior of perturbed eigenvectors for a range of signal-plus-noise matrix models encountered in both statistical and random matrix theoretic settings.
We prove both first-order approximation results (i.e.
sharp deviations) as well as second-order distributional limit theory (i.e.

Built on

Spectral clustering and the high-dimensional stochastic blockmodel
Rohe, K., S. Chatterjee, and B. Yu (2011) · 1915
Earlier work this paper cites.
Stochastic blockmodels: First steps
Holland, P. W., K. B. Laskey, and S. Leinhardt (1983) · 1983
Earlier work this paper cites.
Some limit theorems on the eigenvectors of large dimensional sample covariance matrices
Silverstein, J. W. (1984) · 1984
Earlier work this paper cites.
Principal Component Analysis
Jolliffe, I. T. (1986) · 1986
Earlier work this paper cites.
On the eigenvectors of large dimensional sample covariance matrices
Silverstein, J. W. (1989) · 1989
Earlier work this paper cites.
Matrix Analysis
Bhatia, R. (1997) · 1997
Earlier work this paper cites.
On the distribution of the largest eigenvalue in principal components analysis
Johnstone, I. M. (2001) · 2001
Earlier work this paper cites.
Automatic dimensionality selection from the scree plot via the use of profile likelihood
Zhu, M. and A. Ghodsi (2006) · 2006
Earlier work this paper cites.
Asymptotics of sample eigenstructure for a large dimensional spiked covariance model
Paul, D. (2007) · 2007
Earlier work this paper cites.
Finite sample approximation results for principal component analysis: A matrix perturbation approach
Nadler, B. (2008) · 2008
Earlier work this paper cites.

Similar

Exact matrix completion via convex optimization
Candès, E. J. and B. Recht (2009) · 2009
Cited alongside, same era.
Spectral analysis of large dimensional random matrices
Bai, Z. and J. W. Silverstein (2010) · 2010
Cited alongside, same era.
The eigenvalues and eigenvectors of finite, low rank perturbations of large random matrices
Benaych-Georges, F. and R. R. Nadakuditi (2011) · 2011
Cited alongside, same era.
Spectral statistics of Erdős–Rényi graphs I: Local semicircle law
Erdős, L., A. Knowles, H.-T. Yau, and J. Yin (2013) · 2013
Cited alongside, same era.
Random matrix theory in statistics: A review
Paul, D. and A. Aue (2014) · 2014
Cited alongside, same era.
A useful variant of the Davis–Kahan theorem for statisticians
Yu, Y., T. Wang, and R. J. Samworth (2014) · 2014
Cited alongside, same era.
Consistency of spectral clustering in stochastic block models
Lei, J. and A. Rinaldo (2015) · 2015
Cited alongside, same era.
Delocalization of eigenvectors of random matrices with independent entries
Rudelson, M. and R. Vershynin (2015) · 2015
Cited alongside, same era.
Role of normalization in spectral clustering for stochastic blockmodels
Sarkar, P. and P. J. Bickel (2015) · 2015
Cited alongside, same era.
Entrywise eigenvector analysis of random matrices with low expected rank
Original
Abbe, E., J. Fan, K. Wang, and Y. Zhong (2017) · 2017
Cited alongside, same era.

Then

Concentration and regularization of random graphs
Le, C. M., E. Levina, and R. Vershynin (2017) · 2017
Later among the works it cites.
Estimating mixed memberships with sharp eigenvector deviations
Original
Mao, X., P. Sarkar, and D. Chakrabarti (2017) · 2017
Later among the works it cites.
Asymptotically efficient estimators for stochastic blockmodels: the naive MLE, the rank-constrained MLE, and the spectral
Original
Tang, M., J. Cape, and C. E. Priebe (2017) · 2017
Later among the works it cites.
Rate-optimal perturbation bounds for singular subspaces with applications to high-dimensional statistics
Cai, T. T. and A. Zhang (2018) · 2018
Closest in time.
The two-to-infinity norm and singular subspace geometry with applications to high-dimensional statistics
Original
Cape, J., M. Tang, and C. E. Priebe (2018) · 2018
Closest in time.
Unperturbed: spectral analysis beyond Davis-Kahan
Eldridge, J., M. Belkin, and Y. Wang (2018) · 2018
Closest in time.
An ℓ ∞ \ell_{\infty} eigenvector perturbation bound and its application to robust covariance estimation
Fan, J., W. Wang, and Y. Zhong (2018) · 2018
Closest in time.
Random perturbation of low rank matrices: Improving classical bounds
O’Rourke, S., V. Vu, and K. Wang (2018) · 2018
Closest in time.
Limit theorems for eigenvectors of the normalized Laplacian for random graphs
Tang, M. and C. E. Priebe (2018) · 2018
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…