The spectral norm of random inner-product kernel matrices
From MaRDI portal
Abstract: We study an "inner-product kernel" random matrix model, whose empirical spectral distribution was shown by Xiuyuan Cheng and Amit Singer to converge to a deterministic measure in the large and limit. We provide an interpretation of this limit measure as the additive free convolution of a semicircle law and a Marcenko-Pastur law. By comparing the tracial moments of this random matrix to those of a deformed GUE matrix with the same limiting spectrum, we establish that for odd kernel functions, the spectral norm of this matrix convergences almost surely to the edge of the limiting spectrum. Our study is motivated by the analysis of a covariance thresholding procedure for the statistical detection and estimation of sparse principal components, and our results characterize the limit of the largest eigenvalue of the thresholded sample covariance matrix in the null setting.
Recommendations
Cites work
- scientific article; zbMATH DE number 6026126 (Why is no real title available?)
- scientific article; zbMATH DE number 3037624 (Why is no real title available?)
- A Direct Formulation for Sparse PCA Using Semidefinite Programming
- A limit theorem for the norm of random matrices
- A penalized matrix decomposition, with applications to sparse principal components and canonical correlation analysis
- Adaptive estimation of a quadratic functional by model selection.
- Adaptive thresholding for sparse covariance matrix estimation
- Addition of certain non-commuting random variables
- Asymptotic power of sphericity tests for high-dimensional data
- Asymptotics of sample eigenstructure for a large dimensional spiked covariance model
- Covariance estimation for distributions with \({2+\varepsilon}\) moments
- Covariance regularization by thresholding
- Do semidefinite relaxations solve sparse PCA up to the information limit?
- Edge universality for deformed Wigner matrices
- Eigenvalues of large sample covariance matrices of spiked population models
- Finite sample approximation results for principal component analysis: A matrix perturbation approach
- Fluctuations at the edges of the spectrum of the full rank deformed GUE
- Free convolution with a semicircular distribution and eigenvalues of spiked deformations of Wigner matrices
- Generalized thresholding of large covariance matrices
- High-dimensional analysis of semidefinite relaxations for sparse principal components
- Limit laws for random matrices and free products
- Limit of the smallest eigenvalue of a large dimensional sample covariance matrix
- Minimax bounds for sparse PCA with noisy high-dimensional data
- Minimax estimation of large covariance matrices under \(\ell_1\)-norm
- Multiplicative functions on the lattice of non-crossing partitions and free convolution
- On Bernstein's Approximation Problem
- On consistency and sparsity for principal components analysis in high dimensions
- On the convergence of the extremal eigenvalues of empirical covariance matrices with dependence
- On the empirical distribution of eigenvalues of a class of large dimensional random matrices
- On the free convolution with a semi-circular distribution
- On the limit of the largest eigenvalue of the large dimensional sample covariance matrix
- On universality of local edge regime for the deformed Gaussian unitary ensemble
- Operator norm consistent estimation of large-dimensional sparse covariance matrices
- Optimal detection of sparse principal components in high dimension
- Optimal estimation and rank detection for sparse spiked covariance matrices
- Optimal rates of convergence for sparse covariance matrix estimation
- Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices
- Probability Inequalities for Sums of Independent Random Variables
- Random covariance matrices: universality of local statistics of eigenvalues
- Random matrix approximation of spectra of integral operators
- Rate of convergence in probability to the Marchenko-Pastur law
- Some estimates of norms of random matrices
- Sparse PCA via covariance thresholding
- Sparse PCA: optimal rates and adaptive estimation
- Sparse principal component analysis and iterative thresholding
- Sparse principal component analysis via regularized low rank matrix approximation
- Sparsistency and agnostic inference in sparse PCA
- Spectral norm of random kernel matrices with applications to privacy
- The eigenvalues of random symmetric matrices
- The local relaxation flow approach to universality of the local statistics for random matrices
- The norm of polynomials in large random and deterministic matrices
- The spectrum of kernel random matrices
- The spectrum of random inner-product kernel matrices
- The spectrum of random kernel matrices: universality results for rough and varying kernels
- Universality of covariance matrices
Cited in
(16)- Spectral distribution of large generalized random kernel matrices
- Spectral norm of random kernel matrices with applications to privacy
- On spectral distribution of kernel matrices related to radial basis functions
- Learning curves of generic features maps for realistic datasets with a teacher-student model*
- A note on the large random inner-product kernel matrices
- Eigenvalue distribution of some nonlinear models of random matrices
- Learning low-dimensional nonlinear structures from high-dimensional noisy data: an integral operator approach
- Local and global expansion in random geometric graphs
- Concentration of kernel matrices with application to kernel spectral clustering
- Generalisation error in learning with random features and the hidden manifold model*
- The spectrum of kernel random matrices
- Deep learning: a statistical viewpoint
- Surprises in high-dimensional ridgeless least squares interpolation
- Spectrum of large random inner-product kernel matrices generated from lp ellipsoids
- The spectrum of random kernel matrices: universality results for rough and varying kernels
- Spectral properties of kernel matrices in the flat limit
This page was built for publication: The spectral norm of random inner-product kernel matrices
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1729691)
