Approximate kernel PCA: computational versus statistical trade-off

DOI10.1214/22-AOS2204MaRDI QIDQ2105193zbMATH OpenFDO

Authors Bharath K. Sriperumbudur, Nicholas Sterge

Publication date 8 December 2022

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

Full work available at URL https://arxiv.org/abs/1706.06296

zbMATH Keywords

Bernstein's inequalitycovariance operatorkernel PCAprincipal component analysisrandom feature approximationreproducing kernel Hilbert space

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Factor analysis and principal components; correspondence analysis (62H25)

Recommendations

• Approximate kernel partial least squares
• Accuracy of suboptimal solutions to kernel principal component analysis
• Learning Theory
• On the Nyström method for approximating a gram matrix for improved kernel-based learning
• Statistical properties of kernel principal component analysis

Cites work

• 10.1162/15324430260185619
• Adaptive KPCA Modeling of Nonlinear Systems
• Approximate kernel PCA: computational versus statistical trade-off
• Finding structure with randomness: probabilistic algorithms for constructing approximate matrix decompositions
• scientific article; zbMATH DE number 3719745 (Why is no real title available?)
• scientific article; zbMATH DE number 3576139 (Why is no real title available?)
• scientific article; zbMATH DE number 1540658 (Why is no real title available?)
• Kernel PCA for novelty detection
• Measure theory
• On the Eigenspectrum of the Gram Matrix and the Generalization Error of Kernel-PCA
• On the Nyström method for approximating a gram matrix for improved kernel-based learning
• Optimal rates for the regularized least-squares algorithm
• Randomized sketches for kernels: fast and optimal nonparametric regression
• Scattered Data Approximation
• Some results on Tchebycheffian spline functions and stochastic processes
• Statistical properties of kernel principal component analysis
• Support Vector Machines
• Theory of Reproducing Kernels

Cited in

(9)

• Approximate kernel PCA: computational versus statistical trade-off
• Kernel Principal Component Analysis: Applications, Implementation and Comparison
• Efficient kernel canonical correlation analysis using Nyström approximation
• Approximate Kernel PCA Using Random Features: Computational vs. Statistical Trade-off
• Spectral regularized Kernel two-sample tests
• Random Fourier signature features
• A rainbow in deep network black boxes
• Powerful kernel-based association tests for multivariate responses
• Accuracy of suboptimal solutions to kernel principal component analysis

This page was built for publication: Approximate kernel PCA: computational versus statistical trade-off

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2105193)