A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves (Q2643849): Difference between revisions

From MaRDI portal
Import240304020342 (talk | contribs)
Set profile property.
ReferenceBot (talk | contribs)
Changed an Item
 
(One intermediate revision by one other user not shown)
Property / full work available at URL
 
Property / full work available at URL: https://doi.org/10.1016/j.jat.2006.12.009 / rank
 
Normal rank
Property / OpenAlex ID
 
Property / OpenAlex ID: W2011784318 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q3661894 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Real Interpolation of Sobolev Spaces on Subdomains of Rn / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q4222737 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Universal approximation bounds for superpositions of a sigmoidal function / rank
 
Normal rank
Property / cites work
 
Property / cites work: A better approximation for balls / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q4001895 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q4065742 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Approximation and learning of convex superpositions / rank
 
Normal rank
Property / cites work
 
Property / cites work: The Radon transform / rank
 
Normal rank
Property / cites work
 
Property / cites work: A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training / rank
 
Normal rank
Property / cites work
 
Property / cites work: Geometry and topology of continuous best and near best approximations / rank
 
Normal rank
Property / cites work
 
Property / cites work: Integral combinations of Heavisides / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q3370993 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q4400833 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Comparison of worst case errors in linear and neural network approximation / rank
 
Normal rank
Property / cites work
 
Property / cites work: Uniform approximation by neural networks / rank
 
Normal rank
Property / cites work
 
Property / cites work: Dimension-independent bounds on the degree of approximation by neural networks / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q5848315 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q4938227 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q3952642 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q5809352 / rank
 
Normal rank

Latest revision as of 13:20, 26 June 2024

scientific article
Language Label Description Also known as
English
A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves
scientific article

    Statements

    A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves (English)
    0 references
    0 references
    0 references
    0 references
    27 August 2007
    0 references
    For \(d\) odd, let \(f\) be an \( {\mathbb R}^d \to {\mathbb R}\) function, having continuous partial derivatives \(D^\alpha f(x)\) vanishing as \(| x| \to \infty\) if \(| \alpha| <d\) and satisfying, with some \(\varepsilon >0\), \(D^\alpha f(x)\| x\| ^{d+1+\varepsilon}\to 0\) if \(| \alpha| =d\). Let further \(\theta\) be the Heaviside function, \(\theta(x)=1\) if \( x \geq 0\), \(\theta (x)=0\) if \(x <0\) and let \(\Omega \subset {\mathbb R}^d\) be an arbitrary domain of unit Lebesgue measure. Then for any natural \(n\) and \(i=1, \ldots , n\) there exist real numbers \(b_i, C_i\) and \(d\)-dimensional vectors \(e_i\) such that for \(x \in {\mathbb R}^d\), \(g(x)=\sum_{i=1}^n C_i \theta (v_i \cdot x +b_i)\) one has \[ \| f -g\| _{L_2(\Omega)}\leq k_d \| f\| _{d,1,\infty}n^{-1/2}, \] where \(k_d=2^{1-d}\pi^{1-d/2}d^{d/2}/\Gamma(d/2)\), \(\| f\| _{d,1,\infty}=\max_{| \alpha| =d}\| D^\alpha f\| _{L_1({\mathbb R}^d)}.\) Applications to \(f(x)=\exp(-\| x\| ^2)\) are given.
    0 references
    characteristic functions of closed half-spaces
    0 references
    perceptron neural networks
    0 references
    integral formulas
    0 references
    variation with respect to half-spaces
    0 references
    Radon transform
    0 references
    Gaussian function
    0 references
    rates of approximation
    0 references

    Identifiers