The spectral norm of random inner-product kernel matrices

DOI10.1007/s00440-018-0830-4zbMath1470.60011arXiv1507.05343OpenAlexW2963963733MaRDI QIDQ1729691

Xianqiang Yang

Publication date: 28 February 2019

Published in: Probability Theory and Related Fields (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1507.05343

zbMATH Keywords

random matrixoperator normfree probabilitycovariance thresholding

Mathematics Subject Classification ID

Multivariate distribution of statistics (62H10) Factor analysis and principal components; correspondence analysis (62H25) Random matrices (probabilistic aspects) (60B20) Random matrices (algebraic aspects) (15B52)

Related Items

Deep learning: a statistical viewpoint ⋮ Surprises in high-dimensional ridgeless least squares interpolation ⋮ Learning curves of generic features maps for realistic datasets with a teacher-student model* ⋮ Concentration of kernel matrices with application to kernel spectral clustering ⋮ Learning low-dimensional nonlinear structures from high-dimensional noisy data: an integral operator approach ⋮ Eigenvalue distribution of some nonlinear models of random matrices ⋮ Generalisation error in learning with random features and the hidden manifold model*

Uses Software

• PMA

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A penalized matrix decomposition, with applications to sparse principal components and canonical correlation analysis
• Fluctuations at the edges of the spectrum of the full rank deformed GUE
• Sparse principal component analysis and iterative thresholding
• Minimax bounds for sparse PCA with noisy high-dimensional data
• Asymptotic power of sphericity tests for high-dimensional data
• Covariance estimation for distributions with \({2+\varepsilon}\) moments
• Optimal detection of sparse principal components in high dimension
• Random covariance matrices: universality of local statistics of eigenvalues
• Free convolution with a semicircular distribution and eigenvalues of spiked deformations of Wigner matrices
• On universality of local edge regime for the deformed Gaussian unitary ensemble
• Limit of the smallest eigenvalue of a large dimensional sample covariance matrix
• Optimal rates of convergence for sparse covariance matrix estimation
• High-dimensional analysis of semidefinite relaxations for sparse principal components
• The spectrum of kernel random matrices
• Sparse principal component analysis via regularized low rank matrix approximation
• Covariance regularization by thresholding
• Operator norm consistent estimation of large-dimensional sparse covariance matrices
• Finite sample approximation results for principal component analysis: A matrix perturbation approach
• On the limit of the largest eigenvalue of the large dimensional sample covariance matrix
• Addition of certain non-commuting random variables
• A limit theorem for the norm of random matrices
• The eigenvalues of random symmetric matrices
• Limit laws for random matrices and free products
• Multiplicative functions on the lattice of non-crossing partitions and free convolution
• Adaptive estimation of a quadratic functional by model selection.
• Rate of convergence in probability to the Marchenko-Pastur law
• On the empirical distribution of eigenvalues of a class of large dimensional random matrices
• The norm of polynomials in large random and deterministic matrices
• Random matrix approximation of spectra of integral operators
• Sparsistency and agnostic inference in sparse PCA
• Optimal estimation and rank detection for sparse spiked covariance matrices
• Do semidefinite relaxations solve sparse PCA up to the information limit?
• On the convergence of the extremal eigenvalues of empirical covariance matrices with dependence
• The local relaxation flow approach to universality of the local statistics for random matrices
• Sparse PCA: optimal rates and adaptive estimation
• Universality of covariance matrices
• Eigenvalues of large sample covariance matrices of spiked population models
• Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices
• Sparse PCA via Covariance Thresholding
• THE SPECTRUM OF RANDOM KERNEL MATRICES: UNIVERSALITY RESULTS FOR ROUGH AND VARYING KERNELS
• THE SPECTRUM OF RANDOM INNER-PRODUCT KERNEL MATRICES
• Adaptive Thresholding for Sparse Covariance Matrix Estimation
• Edge universality for deformed Wigner matrices
• On the free convolution with a semi-circular distribution
• Some estimates of norms of random matrices
• On Consistency and Sparsity for Principal Components Analysis in High Dimensions
• Generalized Thresholding of Large Covariance Matrices
• Spectral Norm of Random Kernel Matrices with Applications to Privacy
• Probability Inequalities for Sums of Independent Random Variables
• A Direct Formulation for Sparse PCA Using Semidefinite Programming
• On Bernstein's Approximation Problem

This page was built for publication: The spectral norm of random inner-product kernel matrices