Estimates of the approximation error using Rademacher complexity: Learning vector-valued functions
From MaRDI portal
Publication:1008456
DOI10.1155/2008/640758zbMath1161.41006OpenAlexW2145689061WikidataQ59217212 ScholiaQ59217212MaRDI QIDQ1008456
Marcello Sanguineti, Giorgio Gnecco
Publication date: 30 March 2009
Published in: Journal of Inequalities and Applications (Search for Journal in Brave)
Full work available at URL: https://eudml.org/doc/129901
dynamic programmingvector-valued functionsscalar functionsapproximation errorvariable-basis approximation schemes
Related Items (5)
Suboptimal solutions to dynamic optimization problems via approximations of the policy functions ⋮ Multi-kernel learning for multi-label classification with local Rademacher complexity ⋮ Foundations of Support Constraint Machines ⋮ Functional optimization by variable-basis approximation schemes ⋮ Piecewise convexity of artificial neural networks
Cites Work
- Learning with generalization capability by kernel methods of bounded complexity
- Lipschitz continuous policy functions for strongly concave optimization problems
- From basis functions to basis fields: Vector field approximation from sparse data
- Uniform approximation by neural networks
- On best approximation by ridge functions
- Statistical properties of kernel principal component analysis
- Inequalities for differentiable reproducing kernels and an application to positive integral operators
- Convex kernel underestimation of functions with multiple local minima
- Learning theory estimates via integral operators and their approximations
- On the mathematical foundations of learning
- Approximate Minimization of the Regularized Expected Error over Kernel Models
- Geometric Upper Bounds on Rates of Variable-Basis Approximation
- Universal approximation bounds for superpositions of a sigmoidal function
- Comparison of worst case errors in linear and neural network approximation
- Shannon sampling and function reconstruction from point values
- On Learning Vector-Valued Functions
- Theory of Reproducing Kernels
This page was built for publication: Estimates of the approximation error using Rademacher complexity: Learning vector-valued functions
