A note on the equioscillation theorem for best ridge function approximation
From MaRDI portal
Abstract: We consider the approximation of a continuous function, defined on a compact set of the -dimensional Euclidean space, by sums of two ridge functions. We obtain a necessary and sufficient condition for such a sum to be a best approximation. The result resembles the classical Chebyshev equioscillation theorem for polynomial approximation.
Recommendations
Cites work
- A note on the representation of continuous functions by linear superpositions
- Alternation theorems for functions of several variables
- Approximation by a sum of two algebras. The lightning bolt principle
- Approximation by ridge function fields over compact sets
- Approximation by Ridge Functions and Neural Networks
- Approximation by ridge functions and neural networks with a bounded number of neurons
- Characterization of an extremal sum of ridge functions
- scientific article; zbMATH DE number 3114615 (Why is no real title available?)
- scientific article; zbMATH DE number 3139188 (Why is no real title available?)
- scientific article; zbMATH DE number 3147699 (Why is no real title available?)
- scientific article; zbMATH DE number 89013 (Why is no real title available?)
- scientific article; zbMATH DE number 3455838 (Why is no real title available?)
- scientific article; zbMATH DE number 1405266 (Why is no real title available?)
- scientific article; zbMATH DE number 3216393 (Why is no real title available?)
- scientific article; zbMATH DE number 3295418 (Why is no real title available?)
- scientific article; zbMATH DE number 3399886 (Why is no real title available?)
- scientific article; zbMATH DE number 964891 (Why is no real title available?)
- Interpolation by piecewise-linear radial basis functions. I
- Interpolation by Ridge functions
- Interpolation on lines by ridge functions
- Methods for computing the least deviation from the sums of functions of one variable
- On a smoothness problem in ridge function representation
- On best approximation by ridge functions
- On error formulas for approximation by sums of univariate functions
- On some properties of finite sums of ridge functions defined on convex subsets of \(\mathbb{R}^n\)
- On the approximation of a function of several variables by the sum of functions of fewer variables
- On the continuity of finite sums of ridge functions
- On the representation by linear superpositions
- Optimal reconstruction of a function from its projections
- Projection pursuit
- Ridge functions
- Shift invariant measures and simple spectrum
- Smoothness and uniqueness in ridge function representation
- Uniform approximation by real functions
- When is \(f(x,y)=u(x)+v(y)\)?
- When is \(f(x_1,x_1,\dots,x_n)= u_1(x_1)+ u_2(x_2)+\cdots+ u_n(x_n)\)?
Cited in
(12)- On the representation by bivariate ridge functions
- Characterization of an extremal sum of ridge functions
- scientific article; zbMATH DE number 1259487 (Why is no real title available?)
- scientific article; zbMATH DE number 927447 (Why is no real title available?)
- On the error of approximation by RBF neural networks with two hidden nodes
- 0n the best approximation by ridge functions in the uniform norm
- Approximation error of single hidden layer neural networks with fixed weights
- On the error of approximation by RBF neural networks with two hidden nodes
- Approximation with RBF neural networks using unit smoothing factors and translations
- Mordukhovich derivatives of the set-valued metric projection operator in general Banach spaces
- On the approximation by RBF neural networks with translations
- A representation problem for smooth sums of ridge functions
This page was built for publication: A note on the equioscillation theorem for best ridge function approximation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2403626)
