Concentration of kernel matrices with application to kernel spectral clustering

DOI10.1214/20-AOS1967zbMath1461.62064arXiv1909.03347OpenAlexW3127945797MaRDI QIDQ2656607

Zahra S. Razaee, Arash A. Amini

Publication date: 11 March 2021

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

Full work available at URL: https://arxiv.org/abs/1909.03347

zbMATH Keywords

concentration inequalitieskernel matricesnonasymptotic boundskernel spectral clustering

Mathematics Subject Classification ID

Density estimation (62G07) Estimation in multivariate analysis (62H12) Inequalities; stochastic orderings (60E15) Measures of association (correlation, canonical correlation, etc.) (62H20) Inference from stochastic processes and spectral analysis (62M15)

Related Items

Latent structure blockmodels for Bayesian spectral graph clustering ⋮ Learning low-dimensional nonlinear structures from high-dimensional noisy data: an integral operator approach ⋮ An \({\ell_p}\) theory of PCA and spectral clustering

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• On information plus noise kernel random matrices
• The spectrum of kernel random matrices
• A note on the Hanson-Wright inequality for random vectors with dependencies
• The spectral norm of random inner-product kernel matrices
• Random matrix approximation of spectra of integral operators
• Randomized sketches for kernels: fast and optimal nonparametric regression
• The geometry of kernelized spectral clustering
• Consistency of spectral clustering
• From graph to manifold Laplacian: the convergence rate
• THE SPECTRUM OF RANDOM KERNEL MATRICES: UNIVERSALITY RESULTS FOR ROUGH AND VARYING KERNELS
• THE SPECTRUM OF RANDOM INNER-PRODUCT KERNEL MATRICES
• Clustering for metric and nonmetric distance measures
• On the Eigenspectrum of the Gram Matrix and the Generalization Error of Kernel-PCA
• On Coresets for k-Median and k-Means Clustering in Metric and Euclidean Spaces and Their Applications
• Empirical graph Laplacian approximation of Laplace–Beltrami operators: Large sample results
• High-Dimensional Statistics
• Analysis of spectral clustering algorithms for community detection: the general bipartite setting
• High-Dimensional Probability
• Learning Theory
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• Uniform Convergence of Adaptive Graph-Based Regularization
• Spectral Norm of Random Kernel Matrices with Applications to Privacy
• Learning Theory