VC dimensions of principal component analysis

DOI10.1007/S00454-009-9236-5zbMATH Open1198.62058OpenAlexW2092500953MaRDI QIDQ603853FDOQ603853

Authors: Yohji Akama, Kei Irie, Akitoshi Kawamura, Yasutaka Uwano 

Publication date: 8 November 2010

Published in: Discrete \& Computational Geometry (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s00454-009-9236-5

Recommendations

• VC‐dimension on manifolds: a first approach
• Learning Theory
• Statistical properties of kernel principal component analysis
• VC Dimension and Uniform Learnability of Sparse Polynomials and Rational Functions
• Bounding the Vapnik-Chervonenkis dimension of concept classes parameterized by real numbers

zbMATH Keywords

principal component analysisVC dimensionsWarren's bound

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Eigenvalues, singular values, and eigenvectors (15A18)

Cites Work

• On the distribution of the largest eigenvalue in principal components analysis
• Pattern classification.
• Title not available (Why is that?)
• Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
• Learnability and the Vapnik-Chervonenkis dimension
• Title not available (Why is that?)
• Title not available (Why is that?)
• On the Betti Numbers of Real Varieties
• Lower Bounds for Approximation by Nonlinear Manifolds
• Balls in \(\mathbb{R}^k\) do not cut all subsets of \(k+2\) points
• On the Betti numbers of sign conditions
• An asymptotically tight bound on the number of semi-algebraically connected components of realizable sign conditions
• Entropy and the combinatorial dimension

Cited In (8)

• Title not available (Why is that?)
• The VC dimension of metric balls under Fréchet and Hausdorff distances
• Principal Component Value at Risk
• PROVABLE DIMENSION DETECTION USING PRINCIPAL COMPONENT ANALYSIS
• Training Gaussian mixture models at scale via coresets
• Simple proofs of classical theorems in discrete geometry via the Guth-Katz polynomial partitioning technique
• Strong consistency of factorial \(k\)-means clustering
• Unit distances in three dimensions

This page was built for publication: VC dimensions of principal component analysis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q603853)