Accuracy of suboptimal solutions to kernel principal component analysis

DOI10.1007/S10589-007-9108-YzbMATH Open1179.90325OpenAlexW1963979070MaRDI QIDQ842769FDOQ842769

Authors: Giorgio Gnecco, Marcello Sanguineti 

Publication date: 25 September 2009

Published in: Computational Optimization and Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10589-007-9108-y

Recommendations

• Error bounds for suboptimal solutions to kernel principal component analysis
• Approximate kernel PCA: computational versus statistical trade-off
• Accurate error bounds for the eigenvalues of the kernel matrix
• Kernel Principal Component Analysis: Applications, Implementation and Comparison
• On the predictive potential of kernel principal components
• Robust kernel principal component analysis with optimal mean
• Approximate kernel partial least squares
• Revisiting the predictive power of kernel principal components
• PCA-kernel estimation

zbMATH Keywords

kernel methodsLagrangianprincipal component analysis (PCA)primal and dual problemssuboptimal solutionsregularized optimization problems

Mathematics Subject Classification ID

Programming in abstract spaces (90C48)

Cites Work

• Title not available (Why is that?)
• A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
• Support-vector networks
• Regularization algorithms for learning that are equivalent to multilayer networks
• Universal approximation bounds for superpositions of a sigmoidal function
• Comparison of worst case errors in linear and neural network approximation
• Learning with generalization capability by kernel methods of bounded complexity
• Theory of Reproducing Kernels
• An introduction to support vector machines and other kernel-based learning methods.
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• On the mathematical foundations of learning
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Error Estimates for Approximate Optimization by the Extended Ritz Method
• Title not available (Why is that?)
• 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
• An Approach to Time Series Analysis
• Bounds on rates of variable-basis and neural-network approximation
• Relationship of several variational methods for the approximate solution of ill-posed problems

Cited In (12)

• Functional optimization by variable-basis approximation schemes
• Team optimization problems with Lipschitz continuous strategies
• New insights into Witsenhausen's counterexample
• Can dictionary-based computational models outperform the best linear ones?
• Error bounds for suboptimal solutions to kernel principal component analysis
• A comparison between fixed-basis and variable-basis schemes for function approximation and functional optimization
• The weight-decay technique in learning from data: an optimization point of view
• Approximate kernel PCA: computational versus statistical trade-off
• Unsupervised learning of disentangled representations in deep restricted kernel machines with orthogonality constraints
• Management of water resource systems in the presence of uncertainties by nonlinear approximation techniques and deterministic sampling
• On spectral windows in supervised learning from data
• Convex combination of data matrices: PCA perturbation bounds for multi-objective optimal design of mechanical metafilters

This page was built for publication: Accuracy of suboptimal solutions to kernel principal component analysis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q842769)