Fundamental limits of detection in the spiked Wigner model

We study the fundamental limits of detecting the presence of an additive rank-one perturbation, or spike, to a Wigner matrix. When the spike comes from a prior that is i.i.d. across coordinates, we prove that the log-likelihood ratio of the spiked model against the non-spiked one is asymptotically normal below a certain reconstruction threshold which is not necessarily of a "spectral" nature, and that it is degenerate above. This establishes the maximal region of contiguity between the planted and null models. It is known that this threshold also marks a phase transition for estimating the spike: the latter task is possible above the threshold and impossible below. Therefore, both estimation and detection undergo the same transition in this random matrix model. We also provide further information about the performance of the optimal test. Our proofs are based on Gaussian interpolation methods and a rigorous incarnation of the cavity method, as devised by Guerra and Talagrand in their study of the Sherrington--Kirkpatrick spin-glass model.

[1]  Ankur Moitra,et al.  Optimality and Sub-optimality of PCA I: Spiked Random Matrix Models , 2018, The Annals of Statistics.

[2]  Zongming Ma,et al.  Asymptotic normality and analysis of variance of log-likelihood ratios in spiked random matrix models , 2018, ArXiv.

[3]  Michael I. Jordan,et al.  Detection limits in the high-dimensional spiked rectangular model , 2018, COLT.

[4]  Florent Krzakala,et al.  Estimation in the Spiked Wigner Model: A Short Proof of the Replica Formula , 2018, 2018 IEEE International Symposium on Information Theory (ISIT).

[5]  Jess Banks,et al.  Information-Theoretic Bounds and Phase Transitions in Clustering, Sparse PCA, and Submatrix Localization , 2016, IEEE Transactions on Information Theory.

[6]  Marc Lelarge,et al.  Fundamental limits of symmetric low-rank matrix estimation , 2016, Probability Theory and Related Fields.

[7]  Ankur Moitra,et al.  Optimality and Sub-optimality of PCA for Spiked Random Matrices and Synchronization , 2016, ArXiv.

[8]  Debapratim Banerjee.  Contiguity and non-reconstruction results for planted partition models: the dense case , 2016, 1609.02854.

[9]  Andrea Montanari,et al.  Asymptotic mutual information for the binary stochastic block model , 2016, 2016 IEEE International Symposium on Information Theory (ISIT).

[10]  J. Baik,et al.  Fluctuations of the Free Energy of the Spherical Sherrington–Kirkpatrick Model with Ferromagnetic Interaction , 2016, Annales Henri Poincaré.

[11]  Nicolas Macris,et al.  Mutual information for symmetric rank-one matrix estimation: A proof of the replica formula , 2016, NIPS.

[12]  Florent Krzakala,et al.  Mutual information in rank-one matrix estimation , 2016, 2016 IEEE Information Theory Workshop (ITW).

[13]  E. Dobriban,et al.  Sharp detection in PCA under correlations: all eigenvalues matter , 2016, 1602.06896.

[14]  I. Johnstone,et al.  Testing in high-dimensional spiked models , 2015, The Annals of Statistics.

[15]  J. Baik,et al.  Fluctuations of the Free Energy of the Spherical Sherrington–Kirkpatrick Model , 2015, Journal of Statistical Physics.

[16]  Florent Krzakala,et al.  Phase transitions in sparse PCA , 2015, 2015 IEEE International Symposium on Information Theory (ISIT).

[17]  S. Chatterjee.  Superconcentration and Related Topics , 2014 .

[18]  Marcelo J. Moreira,et al.  Asymptotic power of sphericity tests for high-dimensional data , 2013, 1306.4867.

[19]  Gábor Lugosi,et al.  Concentration Inequalities - A Nonasymptotic Theory of Independence , 2013, Concentration Inequalities.

[20]  Alexei Onatski,et al.  Signal detection in high dimension: The multispiked case , 2012, 1210.5663.

[21]  P. Rigollet,et al.  Optimal detection of sparse principal components in high dimension , 2012, 1202.5070.

[22]  Jianfeng Yao,et al.  On sample eigenvalues in a generalized spiked population model , 2008, J. Multivar. Anal..

[23]  Tim Austin.  Mean field models for spin glasses , 2012 .

[24]  M. Talagrand.  Mean Field Models for Spin Glasses , 2011 .

[25]  Raj Rao Nadakuditi,et al.  The eigenvalues and eigenvectors of finite, low rank perturbations of large random matrices , 2009, 0910.2120.

[26]  I. Johnstone,et al.  On Consistency and Sparsity for Principal Components Analysis in High Dimensions , 2009, Journal of the American Statistical Association.

[27]  B. Nadler.  Finite sample approximation results for principal component analysis: a matrix perturbation approach , 2009, 0901.3245.

[28]  C. Donati-Martin,et al.  The largest eigenvalues of finite rank deformation of large Wigner matrices: Convergence and nonuniversality of the fluctuations. , 2007, 0706.0136.

[29]  Z. Bai,et al.  Central limit theorems for eigenvalues in a spiked population model , 2008, 0806.2503.

[30]  M. Wainwright,et al.  High-dimensional analysis of semidefinite relaxations for sparse principal components , 2008, 2008 IEEE International Symposium on Information Theory.

[31]  D. Féral,et al.  The Largest Eigenvalue of Rank One Deformation of Large Wigner Matrices , 2006, math/0605624.

[32]  D. Paul.  ASYMPTOTICS OF SAMPLE EIGENSTRUCTURE FOR A LARGE DIMENSIONAL SPIKED COVARIANCE MODEL , 2007 .

[33]  S. Péché.  The largest eigenvalue of small rank perturbations of Hermitian random matrices , 2004, math/0411487.

[34]  J. W. Silverstein,et al.  Eigenvalues of large sample covariance matrices of spiked population models , 2004, math/0408165.

[35]  S. Péché,et al.  Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices , 2004, math/0403022.

[36]  F. Guerra.  Broken Replica Symmetry Bounds in the Mean Field Spin Glass Model , 2002, cond-mat/0205123.

[37]  Olivier Ledoit,et al.  Some hypothesis tests for the covariance matrix when the dimension is large compared to the sample size , 2002 .

[38]  I. Johnstone.  On the distribution of the largest eigenvalue in principal components analysis , 2001 .

[39]  西森 秀稔.  Statistical physics of spin glasses and information processing : an introduction , 2001 .

[40]  G. Parisi,et al.  EFFECTIVE POTENTIAL IN GLASSY SYSTEMS : THEORY AND SIMULATIONS , 1997, cond-mat/9711215.

[41]  G. Parisi,et al.  Recipes for metastable states in spin glasses , 1995 .

[42]  D. Ruelle,et al.  Some rigorous results on the Sherrington-Kirkpatrick spin glass model , 1987 .

[43]  M. Mézard,et al.  Spin Glass Theory and Beyond , 1987 .

[44]  H. P..  Annales de l'Institut Henri Poincaré , 1931, Nature.