Generalisation bounds for kernel PCA through PAC-Bayes learning

DOI10.1002/STA4.719MaRDI QIDQ6963065zbMATH OpenFDO

Authors Maxime Haddouche, Benjamin Guedj, John Shawe-Taylor

Publication date 8 July 2025

Published in Stat (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1002/STA4.719

zbMATH Keywords

generalisationkernel methodsPAC-Bayesprincipal component analysis

Mathematics Subject Classification ID

Statistics (62-XX)

Cites work

• Concentration inequalities and moment bounds for sample covariance operators
• High-dimensional statistics. A non-asymptotic viewpoint
• High-probability bounds for the reconstruction error of PCA
• scientific article; zbMATH DE number 5544465 (Why is no real title available?)
• scientific article; zbMATH DE number 7272386 (Why is no real title available?)
• Local Rademacher complexities
• Metric spaces and completely monotone functions.
• Nonasymptotic upper bounds for the reconstruction error of PCA
• On the Eigenspectrum of the Gram Matrix and the Generalization Error of Kernel-PCA
• PAC-Bayesian Generalisation Error Bounds for Gaussian Process Classification
• PAC-Bayesian stochastic model selection
• Regularized kernel PCA for the efficient parameterization of complex geological models
• Statistical properties of kernel principal component analysis
• Support Vector Machines
• Theory of Reproducing Kernels

This page was built for publication: Generalisation bounds for kernel PCA through PAC-Bayes learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6963065)