Fundamental limits of detection in the spiked Wigner model
From MaRDI portal
Publication:2196197
Abstract: 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.
Recommendations
- Optimality and sub-optimality of PCA. I: Spiked random matrix models
- Optimal signal detection in some spiked random matrix models: likelihood ratio tests and linear spectral statistics
- Statistical limits of spiked tensor models
- Limits of spiked random matrices. I
- Phase transition in random tensors with multiple independent spikes
Cites work
- scientific article; zbMATH DE number 1273988 (Why is no real title available?)
- scientific article; zbMATH DE number 1751767 (Why is no real title available?)
- Asymptotic mutual information for the balanced binary stochastic block model
- Asymptotic power of sphericity tests for high-dimensional data
- Asymptotics of sample eigenstructure for a large dimensional spiked covariance model
- Broken replica symmetry bounds in the mean field spin glass model
- Central limit theorems for eigenvalues in a spiked population model
- Concentration inequalities. A nonasymptotic theory of independence
- Contiguity and non-reconstruction results for planted partition models: the dense case
- Deformed ensembles of random matrices
- Eigenvalues of large sample covariance matrices of spiked population models
- Finite sample approximation results for principal component analysis: A matrix perturbation approach
- Fluctuations of the free energy of the spherical Sherrington-Kirkpatrick model
- Fluctuations of the free energy of the spherical Sherrington-Kirkpatrick model with ferromagnetic interaction
- Fundamental limits of symmetric low-rank matrix estimation
- High-dimensional analysis of semidefinite relaxations for sparse principal components
- Information-Theoretic Bounds and Phase Transitions in Clustering, Sparse PCA, and Submatrix Localization
- Mean field models for spin glasses. Volume I: Basic examples.
- On consistency and sparsity for principal components analysis in high dimensions
- On sample eigenvalues in a generalized spiked population model
- On the distribution of the largest eigenvalue in principal components analysis
- Optimal detection of sparse principal components in high dimension
- Optimality and sub-optimality of PCA. I: Spiked random matrix models
- Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices
- Sharp detection in PCA under correlations: all eigenvalues matter
- Signal detection in high dimension: the multispiked case
- Some hypothesis tests for the covariance matrix when the dimension is large compared to the sample size
- Some rigorous results on the Sherrington-Kirkpatrick spin glass model.
- Statistical Physics of Spin Glasses and Information Processing
- Superconcentration and related topics
- The eigenvalues and eigenvectors of finite, low rank perturbations of large random matrices
- The largest eigenvalue of rank one deformation of large Wigner matrices
- The largest eigenvalue of small rank perturbations of Hermitian random matrices
- The largest eigenvalues of finite rank deformation of large Wigner matrices: Convergence and nonuniversality of the fluctuations
Cited in
(13)- High‐dimensional limit theorems for SGD: Effective dynamics and critical scaling
- High-dimensional asymptotics of Langevin dynamics in spiked matrix models
- Free energy fluctuations of the two-spin spherical SK model at critical temperature
- Rapid evaluation of the spectral signal detection threshold and Stieltjes transform
- Optimal signal detection in some spiked random matrix models: likelihood ratio tests and linear spectral statistics
- Fundamental limits of symmetric low-rank matrix estimation
- Notes on computational hardness of hypothesis testing: predictions using the low-degree likelihood ratio
- A Friendly Tutorial on Mean-Field Spin Glass Techniques for Non-Physicists
- Subexponential-time algorithms for sparse PCA
- The adaptive interpolation method for proving replica formulas. Applications to the Curie–Weiss and Wigner spike models
- Phase transition in random tensors with multiple independent spikes
- Optimality and sub-optimality of PCA. I: Spiked random matrix models
- The decimation scheme for symmetric matrix factorization
This page was built for publication: Fundamental limits of detection in the spiked Wigner model
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2196197)
