Bounds on rates of variable-basis and neural-network approximation
From MaRDI portal
Publication:4544714
DOI10.1109/18.945285zbMath1008.41012OpenAlexW2132314398MaRDI QIDQ4544714
Vera Kurková, Marcello Sanguineti
Publication date: 4 August 2002
Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1109/18.945285
Neural nets applied to problems in time-dependent statistical mechanics (82C32) Approximation by other special function classes (41A30) Neural nets and related approaches to inference from stochastic processes (62M45)
Related Items (35)
Deep learning: a statistical viewpoint ⋮ When is approximation by Gaussian networks necessarily a linear process? ⋮ Accuracy of suboptimal solutions to kernel principal component analysis ⋮ Two-Layer Neural Networks with Values in a Banach Space ⋮ Lower estimation of approximation rate for neural networks ⋮ Uniform approximation rates and metric entropy of shallow neural networks ⋮ Optimization of approximating networks for optimal fault diagnosis ⋮ On the tractability of multivariate integration and approximation by neural networks ⋮ Probabilistic lower bounds for approximation by shallow perceptron networks ⋮ Wavelet neural networks functional approximation and application ⋮ A deep network construction that adapts to intrinsic dimensionality beyond the domain ⋮ Characterization of the variation spaces corresponding to shallow neural networks ⋮ Gradient descent on infinitely wide neural networks: global convergence and generalization ⋮ The ridge function representation of polynomials and an application to neural networks ⋮ Can dictionary-based computational models outperform the best linear ones? ⋮ 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 ⋮ Approximation and learning by greedy algorithms ⋮ 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 ⋮ Weighted quadrature formulas and approximation by zonal function networks on the sphere ⋮ The weight-decay technique in learning from data: an optimization point of view ⋮ Geometric Rates of Approximation by Neural Networks ⋮ Approximating networks and extended Ritz method for the solution of functional optimization problems ⋮ Optimization based on quasi-Monte Carlo sampling to design state estimators for non-linear systems ⋮ Value and Policy Function Approximations in Infinite-Horizon Optimization Problems ⋮ Approximation schemes for functional optimization problems ⋮ Approximative compactness of linear combinations of characteristic functions ⋮ Super-resolution meets machine learning: approximation of measures ⋮ Unnamed Item ⋮ Rates of minimization of error functionals over Boolean variable-basis functions ⋮ The Barron space and the flow-induced function spaces for neural network models ⋮ High-order approximation rates for shallow neural networks with cosine and \(\mathrm{ReLU}^k\) activation functions
This page was built for publication: Bounds on rates of variable-basis and neural-network approximation
