On information plus noise kernel random matrices
From MaRDI portal
Publication:605943
DOI10.1214/10-AOS801zbMath1200.62056arXiv1011.2660MaRDI QIDQ605943
Publication date: 15 November 2010
Published in: The Annals of Statistics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1011.2660
random matrix theoryconcentration of measuremachine learningmultivariate statistical analysishigh-dimensional inferencekernel matrices
Multivariate distribution of statistics (62H10) Random matrices (algebraic aspects) (15B52) Limit theorems in probability theory (60F99)
Related Items (24)
Embedding Riemannian manifolds by the heat kernel of the connection Laplacian ⋮ Concentration of kernel matrices with application to kernel spectral clustering ⋮ Lévy-Khintchine random matrices and the Poisson weighted infinite skeleton tree ⋮ Scaling positive random matrices: concentration and asymptotic convergence ⋮ Covariance discriminative power of kernel clustering methods ⋮ Robust Inference of Manifold Density and Geometry by Doubly Stochastic Scaling ⋮ Learning low-dimensional nonlinear structures from high-dimensional noisy data: an integral operator approach ⋮ Spatiotemporal analysis using Riemannian composition of diffusion operators ⋮ Graph connection Laplacian and random matrices with random blocks ⋮ Random matrix theory in statistics: a review ⋮ Think globally, fit locally under the manifold setup: asymptotic analysis of locally linear embedding ⋮ On the inference about the spectral distribution of high-dimensional covariance matrix based on high-frequency noisy observations ⋮ Optimizing shrinkage curves and application in image denoising ⋮ Perturbation of the eigenvectors of the graph Laplacian: application to image denoising ⋮ Graph connection Laplacian methods can be made robust to noise ⋮ Linearized two-layers neural networks in high dimension ⋮ Explore Intrinsic Geometry of Sleep Dynamics and Predict Sleep Stage by Unsupervised Learning Techniques ⋮ A Geometrical Method for Low-Dimensional Representations of Simulations ⋮ The Steerable Graph Laplacian and its Application to Filtering Image Datasets ⋮ Wave-shape oscillatory model for nonstationary periodic time series analysis ⋮ Covariate Regularized Community Detection in Sparse Graphs ⋮ Doubly Stochastic Normalization of the Gaussian Kernel Is Robust to Heteroskedastic Noise ⋮ Latent common manifold learning with alternating diffusion: analysis and applications ⋮ THE SPECTRUM OF RANDOM KERNEL MATRICES: UNIVERSALITY RESULTS FOR ROUGH AND VARYING KERNELS
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- The spectrum of kernel random matrices
- Towards a theoretical foundation for Laplacian-based manifold methods
- 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 distribution of the largest eigenvalue in principal components analysis
- Random matrix approximation of spectra of integral operators
- Consistency of spectral clustering
- 10.1162/153244303768966085
- Modern Multivariate Statistical Techniques
- Asymptotic Statistics
- Learning Theory
- Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
This page was built for publication: On information plus noise kernel random matrices