THE SPECTRUM OF RANDOM INNER-PRODUCT KERNEL MATRICES

DOI10.1142/S201032631350010XMaRDI QIDQ2871282

Amit Singer, Xiuyuan Cheng

Publication date: 22 January 2014

Published in: Random Matrices: Theory and Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1202.3155

zbMATH Keywords

Stieltjes transformHermite polynomialskernel matriceslimiting spectrum

Mathematics Subject Classification ID

Multivariate distribution of statistics (62H10) Limit theorems in probability theory (60F99)

Related Items

Deep learning: a statistical viewpoint ⋮ Surprises in high-dimensional ridgeless least squares interpolation ⋮ Noisy dynamic simulations in the presence of symmetry: data alignment and model reduction ⋮ Learning curves of generic features maps for realistic datasets with a teacher-student model* ⋮ 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 ⋮ Covariance discriminative power of kernel clustering methods ⋮ Learning low-dimensional nonlinear structures from high-dimensional noisy data: an integral operator approach ⋮ Graph connection Laplacian and random matrices with random blocks ⋮ The spectral norm of random inner-product kernel matrices ⋮ Spectral distribution of large generalized random kernel matrices ⋮ Eigenvalue distribution of some nonlinear models of random matrices ⋮ Nonlinear random matrix theory for deep learning ⋮ A note on the large random inner-product kernel matrices ⋮ Generalisation error in learning with random features and the hidden manifold model*

Cites Work

• Unnamed Item
• The spectrum of kernel random matrices
• Covariance regularization by thresholding
• Operator norm consistent estimation of large-dimensional sparse covariance matrices
• Spectral analysis of large dimensional random matrices
• A note on universality of the distribution of the largest eigenvalues in certain sample covariance matrices
• Universality at the edge of the spectrum in Wigner random matrices.
• On the distribution of the largest eigenvalue in principal components analysis
• On orthogonal and symplectic matrix ensembles
• Random matrices: Universality of local eigenvalue statistics up to the edge
• Random matrix approximation of spectra of integral operators
• Tracy-Widom limit for the largest eigenvalue of a large class of complex sample covariance matrices
• Diffusion maps
• Vector diffusion maps and the connection Laplacian
• Viewing Angle Classification of Cryo-Electron Microscopy Images Using Eigenvectors
• A law of large numbers for finite-range dependent random matrices
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation