Learning low-dimensional nonlinear structures from high-dimensional noisy data: an integral operator approach (Q6183757)

scientific article; zbMATH DE number 7783517

Language	Label	Description	Also known as
English	Learning low-dimensional nonlinear structures from high-dimensional noisy data: an integral operator approach	scientific article; zbMATH DE number 7783517

Statements

instance of

scholarly article

0 references

title

Learning low-dimensional nonlinear structures from high-dimensional noisy data: an integral operator approach (English)

0 references

0 references

0 references

The Annals of Statistics

0 references

publication date

4 January 2024

0 references

full work available at URL

https://arxiv.org/abs/2203.00126

0 references

https://projecteuclid.org/journals/annals-of-statistics/volume-51/issue-4/Learning-low-dimensional-nonlinear-structures-from-high-dimensional-noisy-data/10.1214/23-AOS2306.full

0 references

zbMATH Keywords

high-dimensional data

0 references

kernel method

0 references

manifold learning

0 references

nonlinear dimension reduction

0 references

spectral method

0 references

MaRDI profile type

MaRDI publication profile

0 references

cites work

An ${\ell_p}$ theory of PCA and spectral clustering

0 references

Concentration of kernel matrices with application to kernel spectral clustering

0 references

Q2933864

0 references

Statistical inference for principal components of spiked covariance matrices

0 references

Singular vector and singular subspace distribution for the matrix denoising model

0 references

A Riemann-Stein kernel method

0 references

The Dynamics of Message Passing on Dense Graphs, with Applications to Compressed Sensing

0 references

Laplacian Eigenmaps for Dimensionality Reduction and Data Representation

0 references

Q5488485

0 references

Q4836494

0 references

Q5483032

0 references

Statistical properties of kernel principal component analysis

0 references

On Euclidean random matrices in high dimension

0 references

Modern multidimensional scaling. Theory and applications.

0 references

Q3174041

0 references

Lipschitz Regularity of Graph Laplacians on Random Data Clouds

0 references

Spectral Methods for Data Science: A Statistical Perspective

0 references

Local Linear Regression on Manifolds and Its Geometric Interpretation

0 references

THE SPECTRUM OF RANDOM INNER-PRODUCT KERNEL MATRICES

0 references

Diffusion maps

0 references

On the Spectral Property of Kernel-Based Sensor Fusion Algorithms of High Dimensional Data

0 references

THE SPECTRUM OF RANDOM KERNEL MATRICES: UNIVERSALITY RESULTS FOR ROUGH AND VARYING KERNELS

0 references

Hessian eigenmaps: Locally linear embedding techniques for high-dimensional data

0 references

Graph Based Gaussian Processes on Restricted Domains

0 references

Spectral convergence of graph Laplacian and heat kernel reconstruction in $L^\infty$ from random samples

0 references

The spectrum of kernel random matrices

0 references

On information plus noise kernel random matrices

0 references

Graph connection Laplacian methods can be made robust to noise

0 references

An $\ell_{\infty}$ Eigenvector Perturbation Bound and Its Application to Robust Covariance Estimation

0 references

The spectral norm of random inner-product kernel matrices

0 references

Q2810911

0 references

Error estimates for spectral convergence of the graph Laplacian on random geometric graphs toward the Laplace-Beltrami operator

0 references

Empirical graph Laplacian approximation of Laplace–Beltrami operators: Large sample results

0 references

Kernel methods in machine learning

0 references

Improving Spectral Clustering Using the Asymptotic Value of the Normalized Cut

0 references

On the distribution of the largest eigenvalue in principal components analysis

0 references

Principal component analysis.

0 references

Q3965154

0 references

Kernel Methods and Machine Learning

0 references

Nonlinear Dimensionality Reduction

0 references

Clustering with t-SNE, Provably

0 references

Optimality of spectral clustering in the Gaussian mixture model

0 references

DISTRIBUTION OF EIGENVALUES FOR SOME SETS OF RANDOM MATRICES

0 references

The imbedding problem for Riemannian manifolds

0 references

Q2896059

0 references

Q2755103

0 references

Scalability and robustness of spectral embedding: landmark diffusion is all you need

0 references

Data spectroscopy: eigenspaces of convolution operators and clustering

0 references

From graph to manifold Laplacian: the convergence rate

0 references

Vector diffusion maps and the connection Laplacian

0 references

Spectral convergence of the connection Laplacian from random samples

0 references

Learning theory estimates via integral operators and their approximations

0 references

Geometry on probability spaces

0 references

Q3096207

0 references

High-Dimensional Probability

0 references

Consistency of spectral clustering

0 references

Q5053187

0 references

Q3394879

0 references

Spectral Convergence of Diffusion Maps: Improved Error Bounds and an Alternative Normalization

0 references

Think globally, fit locally under the manifold setup: asymptotic analysis of locally linear embedding

0 references

Principal Manifolds and Nonlinear Dimensionality Reduction via Tangent Space Alignment

0 references

Analysis of spectral clustering algorithms for community detection: the general bipartite setting

0 references

Identifiers

arXiv ID

2203.00126

0 references

Mathematics Subject Classification ID

0 references

0 references

0 references

0 references

0 references

0 references

Sitelinks

Mathematics(1 entry)

mardi Publication:6183757