The spectrum of kernel random matrices

DOI10.1214/08-AOS648zbMath1181.62078arXiv1001.0492OpenAlexW3102351945MaRDI QIDQ847627

Noureddine El Karoui

Publication date: 19 February 2010

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1001.0492

zbMATH Keywords

random matrix theoryconcentration of measuremachine learningmultivariate statistical analysishigh-dimensional inferencecovariance matriceskernel matriceseigenvalues of covariance matricesHadamard matrix functions

Mathematics Subject Classification ID

Multivariate distribution of statistics (62H10) Factor analysis and principal components; correspondence analysis (62H25) Characterization and structure theory for multivariate probability distributions; copulas (62H05) Eigenvalues, singular values, and eigenvectors (15A18) Random matrices (algebraic aspects) (15B52) Limit theorems in probability theory (60F99)

Related Items (42)

Deep learning: a statistical viewpoint ⋮ Communication-efficient distributed estimator for generalized linear models with a diverging number of covariates ⋮ Surprises in high-dimensional ridgeless least squares interpolation ⋮ Kernel spectral clustering of large dimensional data ⋮ Learning curves of generic features maps for realistic datasets with a teacher-student model* ⋮ A random matrix approach to neural networks ⋮ Spectrum of large random inner-product kernel matrices generated from l_p ellipsoids ⋮ Unnamed Item ⋮ Spectrum of large euclidean random matrices generated from l_p ellipsoids ⋮ Concentration of kernel matrices with application to kernel spectral clustering ⋮ On the spectrum of dense random geometric graphs ⋮ On information plus noise kernel random matrices ⋮ On the normalized Laplacian spectra of random geometric graphs ⋮ Conditional predictive inference for stable algorithms ⋮ Covariance discriminative power of kernel clustering methods ⋮ On the limiting spectral distributions of stochastic block models ⋮ Just interpolate: kernel ``ridgeless regression can generalize ⋮ Learning low-dimensional nonlinear structures from high-dimensional noisy data: an integral operator approach ⋮ Limiting spectral distribution of stochastic block model ⋮ Graph connection Laplacian and random matrices with random blocks ⋮ The smallest eigenvalues of random kernel matrices: asymptotic results on the min kernel ⋮ Random matrix theory in statistics: a review ⋮ The spectral norm of random inner-product kernel matrices ⋮ Spectral Properties of Kernel Matrices in the Flat Limit ⋮ On the Numerical Rank of Radial Basis Function Kernels in High Dimensions ⋮ On Rayleigh-type formulas for a non-local boundary value problem associated with an integral operator commuting with the Laplacian ⋮ Perturbation of the eigenvectors of the graph Laplacian: application to image denoising ⋮ Feature augmentation for the inversion of the Fourier transform with limited data ⋮ Linearized two-layers neural networks in high dimension ⋮ Learning via variably scaled kernels ⋮ Spectral distribution of large generalized random kernel matrices ⋮ Eigenvalue distribution of some nonlinear models of random matrices ⋮ Concentration of measure and spectra of random matrices: applications to correlation matrices, elliptical distributions and beyond ⋮ A note on the Pennington-Worah distribution ⋮ THE SPECTRUM OF RANDOM KERNEL MATRICES: UNIVERSALITY RESULTS FOR ROUGH AND VARYING KERNELS ⋮ Nonlinear random matrix theory for deep learning ⋮ Distributions of eigenvalues of large Euclidean matrices generated from \(l_p\) balls and spheres ⋮ A note on the large random inner-product kernel matrices ⋮ Eigen-analysis of nonlinear PCA with polynomial kernels ⋮ THE SPECTRUM OF RANDOM INNER-PRODUCT KERNEL MATRICES ⋮ The conjugate gradient algorithm on a general class of spiked covariance matrices ⋮ For interpolating kernel machines, minimizing the norm of the ERM solution maximizes stability

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Characteristic vectors of bordered matrices with infinite dimensions
• No eigenvalues outside the support of the limiting empirical spectral distribution of a separable covariance matrix
• Operator norm consistent estimation of large-dimensional sparse covariance matrices
• Concentration of measure and spectra of random matrices: applications to correlation matrices, elliptical distributions and beyond
• On the limit of the largest eigenvalue of the large dimensional sample covariance matrix
• A limit theorem for the norm of random matrices
• The strong limits of random matrix spectra for sample matrices of independent elements
• No eigenvalues outside the support of the limiting spectral distribution of large-dimensional sample covariance matrices
• Level-spacing distributions and the Airy kernel
• Exact separation of eigenvalues of large dimensional sample covariance matrices
• Correlation functions, cluster functions, and spacing distributions for random matrices
• On the distribution of the largest eigenvalue in principal components analysis
• Necessary and sufficient condition that the limit of Stieltjes transforms is a Stieltjes transform
• Strong convergence of the empirical distribution of eigenvalues of large dimensional random matrices
• On orthogonal and symplectic matrix ensembles
• The spectrum edge of random matrix ensembles.
• Shape fluctuations and random matrices
• Random matrix approximation of spectra of integral operators
• Tracy-Widom limit for the largest eigenvalue of a large class of complex sample covariance matrices
• On asymptotics of eigenvectors of large sample covariance matrix
• Eigenvalues of large sample covariance matrices of spiked population models
• Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices
• 10.1162/153244303768966085
• Eigenvalues of Euclidean random matrices
• Spectral properties of distance matrices
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• Traces and determinants of linear operators

This page was built for publication: The spectrum of kernel random matrices