On best approximation by ridge functions

DOI10.1006/jath.1998.3304zbMath0939.41014OpenAlexW1984137599MaRDI QIDQ1300146

Publication date: 3 July 2000

Published in: Journal of Approximation Theory (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1006/jath.1998.3304

zbMATH Keywords

manifolds best approximation ridge functions multivariate functions Sobolev classes

Mathematics Subject Classification ID

Best approximation, Chebyshev systems (41A50) Abstract approximation theory (approximation in normed linear spaces and other abstract spaces) (41A65) Approximation by other special function classes (41A30)

Related Items

Neural network approximation, Linear and nonlinear approximation of spherical radial basis function networks, ON THE LOWER BOUND IN THE PROBLEM OF APPROXIMATE RECONSTRUCTION OF FUNCTIONS BY VALUES OF THE RADON TRANSFORM, Approximation by ridge function fields over compact sets, Approximation by ridge functions and neural networks with a bounded number of neurons, Lower estimation of approximation rate for neural networks, Geometric properties of the ridge function manifold, Approximation of Sobolev classes by polynomials and ridge functions, On some properties of finite sums of ridge functions defined on convex subsets of \(\mathbb{R}^n\), Deep distributed convolutional neural networks: Universality, On covering numbers of sublevel sets of analytic functions, Consistency of Ridge Function Fields for Varying Nonparametric Regression, A note on the equioscillation theorem for best ridge function approximation, A generative model for fBm with deep ReLU neural networks, On the value of partial information for learning from examples, On the continuity of finite sums of ridge functions, Theory of deep convolutional neural networks. III: Approximating radial functions, Approximation capabilities of neural networks on unbounded domains, On sharpness of error bounds for multivariate neural network approximation, Approximating smooth and sparse functions by deep neural networks: optimal approximation rates and saturation, The Kolmogorov-Arnold representation theorem revisited, On the representation by linear superpositions, On a smoothness problem in ridge function representation, Deep learning theory of distribution regression with CNNs, Representation of polynomials by linear combinations of radial basis functions, Approximation of curve-based sleeve functions in high dimensions, Continuous sums of ridge functions on a convex body and the class VMO, Approximation by sums of ridge functions with fixed directions, APPROXIMATION BY SPHERICAL NEURAL NETWORKS WITH ZONAL FUNCTIONS, Essential rate for approximation by spherical neural networks, The ridge function representation of polynomials and an application to neural networks, Approximation by polynomials and ridge functions of classes of \(s\)-monotone radial functions, Unnamed Item, Approximation Properties of Ridge Functions and Extreme Learning Machines, On some properties of smooth sums of ridge functions, On lower bounds in radial basis approximation, Complexity of Gaussian-radial-basis networks approximating smooth functions, Linearized two-layers neural networks in high dimension, Some problems in the theory of ridge functions, Limitations of shallow nets approximation, A note on continuous sums of ridge functions, Estimates of the approximation error using Rademacher complexity: Learning vector-valued functions, Complexity of Shallow Networks Representing Finite Mappings, On the representation by bivariate ridge functions, The essential rate of approximation for radial function manifold, A representation problem for smooth sums of ridge functions, On the approximation of functional classes equipped with a uniform measure using ridge functions, Deep ReLU neural networks overcome the curse of dimensionality for partial integrodifferential equations, Approximating functions with multi-features by deep convolutional neural networks, On best approximation of classes by radial functions, High-order approximation rates for shallow neural networks with cosine and \(\mathrm{ReLU}^k\) activation functions

Cites Work