Best approximation by linear combinations of characteristic functions of half-spaces.
The paper is devoted to an important type of nonlinear approximation, i.e., variable-basis approximation, where the set of approximating functions is formed by linear combinations of \(n\) functions from a certain set. The main result shows that for any positive integer \(n\) and any function \(f\) in \(\mathcal{L}_{p}([0,1]^{d})\), with \(p\in [1,\infty )\), there exist \(n\) half-spaces such that \(f\) has a best approximation by a linear combination of the characteristic functions of these half-spaces.
- scientific article; zbMATH DE number 1524449
- Approximative compactness of linear combinations of characteristic functions
- The characterization of the best approximant for the multivariable functions in the space \(L_{p_1,\dots,p_n;\Omega }\)
- \(L_ p\) approximation by subsets of convex functions of several variables
- Non-linear approximation of functions with mixed smoothness by sets of finite pseudo-dimension
- A better approximation for balls
- Approximation and learning of convex superpositions
- Approximation by superposition of sigmoidal and radial basis functions
- Continuity of approximation by neural networks in \(L_p\) spaces
- Geometry and topology of continuous best and near best approximations
- scientific article; zbMATH DE number 3162185 (Why is no real title available?)
- scientific article; zbMATH DE number 1405266 (Why is no real title available?)
- scientific article; zbMATH DE number 3314644 (Why is no real title available?)
- Networks and the best approximation property
- Neural Networks for Localized Approximation
- Optimal nonlinear approximation
- Approximation schemes for functional optimization problems
- Single image super-resolution by approximated Heaviside functions
- Minimization of Error Functionals over Perceptron Networks
- Integral combinations of Heavisides
- Projections and Non-Linear Approximation in the Space BV($\mathbb{R}^d$)
- On the existence of minimizers in shallow residual ReLU neural network optimization landscapes
- On the existence of optimal shallow feedforward networks with ReLU activation
- Replacing points by compacta in neural network approximation
- Approximative compactness of linear combinations of characteristic functions
This page was built for publication: Best approximation by linear combinations of characteristic functions of half-spaces.
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1395802)
