Error Estimates for Approximate Optimization by the Extended Ritz Method

DOI10.1137/S1052623403426507zbMath1074.49008MaRDI QIDQ5317507

Vera Kurková, Marcello Sanguineti

Publication date: 16 September 2005

Published in: SIAM Journal on Optimization (Search for Journal in Brave)

zbMATH Keywords

dimensionalityfunctional optimization(extended) Ritz methodconvex best approximation problemslearning from data by kernel methodsrates of convergence of suboptimal solutions

Mathematics Subject Classification ID

Applications of mathematical programming (90C90) Numerical optimization and variational techniques (65K10) Learning and adaptive systems in artificial intelligence (68T05) Newton-type methods (49M15) Best approximation, Chebyshev systems (41A50)

Related Items (28)

Epsilon penalty method combined with an extension of the Ritz method for solving a class of fractional optimal control problems with mixed inequality constraints ⋮ On the curse of dimensionality in the Ritz method ⋮ Accuracy of suboptimal solutions to kernel principal component analysis ⋮ Some properties on quadratic infinite programs of integral type ⋮ Suboptimal solutions to dynamic optimization problems via approximations of the policy functions ⋮ Minimizing sequences for a family of functional optimal estimation problems ⋮ A comparison between fixed-basis and variable-basis schemes for function approximation and functional optimization ⋮ Complexity estimates based on integral transforms induced by computational units ⋮ Combination of epsilon and Ritz methods with multiscaling basis for solving a class of fractional optimal control problems ⋮ Approximate dynamic programming for stochastic \(N\)-stage optimization with application to optimal consumption under uncertainty ⋮ Regularization Techniques and Suboptimal Solutions to Optimization Problems in Learning from Data ⋮ Functional optimal estimation problems and their solution by nonlinear approximation schemes ⋮ New insights into Witsenhausen's counterexample ⋮ Functional optimization by variable-basis approximation schemes ⋮ Error bounds for suboptimal solutions to kernel principal component analysis ⋮ Estimates of variation with respect to a set and applications to optimization problems ⋮ Some comparisons of complexity in dictionary-based and linear computational models ⋮ Learning with generalization capability by kernel methods of bounded complexity ⋮ Management of water resource systems in the presence of uncertainties by nonlinear approximation techniques and deterministic sampling ⋮ Nonparametric nonlinear regression using polynomial and neural approximators: a numerical comparison ⋮ The weight-decay technique in learning from data: an optimization point of view ⋮ Unnamed Item ⋮ Value and Policy Function Approximations in Infinite-Horizon Optimization Problems ⋮ Approximation schemes for functional optimization problems ⋮ Suboptimal Policies for Stochastic $$N$$-Stage Optimization: Accuracy Analysis and a Case Study from Optimal Consumption ⋮ An Integral Upper Bound for Neural Network Approximation ⋮ An Approach to the Conditional Error Rate Principle with Nuisance Parameters ⋮ Rates of minimization of error functionals over Boolean variable-basis functions

This page was built for publication: Error Estimates for Approximate Optimization by the Extended Ritz Method