Learning with generalization capability by kernel methods of bounded complexity

DOI10.1016/J.JCO.2004.11.002MaRDI QIDQ558012zbMATH OpenOpenAlexFDO

Authors Marcello Sanguineti, Věra Kůrková

Publication date 30 June 2005

Published in Journal of Complexity (Search for Journal in Brave)

Full work available at URL http://www.nusl.cz/ntk/nusl-34137

zbMATH Keywords

GeneralizationKernel methodsMinimization of regularized empirical errorsModel complexitySupervised learningUpper bounds on rates of approximate optimization

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Sampling theory, sample surveys (62D05) Computational learning theory (68Q32)

Recommendations

• Learning Bounds for Support Vector Machines with Learned Kernels
• Refined generalization bounds of gradient learning over reproducing kernel Hilbert spaces
• Learning Bounds for Kernel Regression Using Effective Data Dimensionality
• Multiple kernel learning with the generalization error bound of support vector machine
• Error bounds for learning the kernel
• Learnability in Hilbert spaces with reproducing kernels
• A sparsity driven kernel machine based on minimizing a generalization error bound
• scientific article; zbMATH DE number 7646022

Cites work

• scientific article; zbMATH DE number 1804115 (Why is no real title available?)
• scientific article; zbMATH DE number 3126094 (Why is no real title available?)
• scientific article; zbMATH DE number 4004880 (Why is no real title available?)
• scientific article; zbMATH DE number 3658929 (Why is no real title available?)
• scientific article; zbMATH DE number 3772326 (Why is no real title available?)
• scientific article; zbMATH DE number 41891 (Why is no real title available?)
• scientific article; zbMATH DE number 45848 (Why is no real title available?)
• scientific article; zbMATH DE number 46301 (Why is no real title available?)
• scientific article; zbMATH DE number 3551792 (Why is no real title available?)
• scientific article; zbMATH DE number 1206370 (Why is no real title available?)
• scientific article; zbMATH DE number 1332320 (Why is no real title available?)
• scientific article; zbMATH DE number 1182753 (Why is no real title available?)
• scientific article; zbMATH DE number 194544 (Why is no real title available?)
• scientific article; zbMATH DE number 2115052 (Why is no real title available?)
• scientific article; zbMATH DE number 778115 (Why is no real title available?)
• scientific article; zbMATH DE number 3227378 (Why is no real title available?)
• scientific article; zbMATH DE number 3257595 (Why is no real title available?)
• A Correspondence Between Bayesian Estimation on Stochastic Processes and Smoothing by Splines
• A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
• An Approach to Time Series Analysis
• Best choices for regularization parameters in learning theory: on the bias-variance problem.
• Bounds on rates of variable-basis and neural-network approximation
• Comparison of worst case errors in linear and neural network approximation
• Error Estimates for Approximate Optimization by the Extended Ritz Method
• Metric spaces and completely monontone functions
• On the mathematical foundations of learning
• On uniformly convex functionals
• Perturbations, approximations and sensitivity analysis of optimal control systems
• Regularization algorithms for learning that are equivalent to multilayer networks
• Some remarks on the condition number of a real random square matrix
• The geometry of ill-conditioning
• Theory of Reproducing Kernels
• Universal approximation bounds for superpositions of a sigmoidal function
• Well-posed optimization problems

Cited in

(34)

• Power series kernels
• New insights into Witsenhausen's counterexample
• Deterministic error bounds for kernel-based learning techniques under bounded noise
• scientific article; zbMATH DE number 2033148 (Why is no real title available?)
• Estimates of the approximation error using Rademacher complexity: Learning vector-valued functions
• Accuracy of suboptimal solutions to kernel principal component analysis
• Estimates of variation with respect to a set and applications to optimization problems
• Generalization performance of multi-category kernel machines
• Regularization techniques and suboptimal solutions to optimization problems in learning from data
• The weight-decay technique in learning from data: an optimization point of view
• Generalization bounds of regularization algorithms derived simultaneously through hypothesis space complexity, algorithmic stability and data quality
• Generalization bounds for learning with linear, polygonal, quadratic and conic side knowledge
• Complexity control in statistical learning
• Refined generalization bounds of gradient learning over reproducing kernel Hilbert spaces
• Management of water resource systems in the presence of uncertainties by nonlinear approximation techniques and deterministic sampling
• scientific article; zbMATH DE number 6401690 (Why is no real title available?)
• Generalization performance of regularization networks and support vector machines via entropy numbers of compact operators
• On spectral windows in supervised learning from data
• Functional optimal estimation problems and their solution by nonlinear approximation schemes
• Learning with boundary conditions
• A recursive algorithm for nonlinear least-squares problems
• Regularized vector field learning with sparse approximation for mismatch removal
• scientific article; zbMATH DE number 5957262 (Why is no real title available?)
• Sparse representation in Szegő kernels through reproducing kernel Hilbert space theory with applications
• Generalization bounds of a compressed regression learning algorithm
• Approximate minimization of the regularized expected error over kernel models
• Generalization error of minimum weighted norm and kernel interpolation
• Generalization error rates in kernel regression: the crossover from the noiseless to noisy regime*
• Radial fuzzy systems
• Universal discrete-time reservoir computers with stochastic inputs and linear readouts using non-homogeneous state-affine systems
• Rates of minimization of error functionals over Boolean variable-basis functions
• Error bounds for learning the kernel
• Learning Bounds for Kernel Regression Using Effective Data Dimensionality
• Convolutional spectral kernel learning with generalization guarantees

This page was built for publication: Learning with generalization capability by kernel methods of bounded complexity

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q558012)