Nonlinear approximation using Gaussian kernels (Q982495): Difference between revisions

From MaRDI portal
m rollbackEdits.php mass rollback
Tag: Rollback
ReferenceBot (talk | contribs)
Changed an Item
 
(2 intermediate revisions by 2 users not shown)
Property / OpenAlex ID
 
Property / OpenAlex ID: W2132221321 / rank
 
Normal rank
Property / arXiv ID
 
Property / arXiv ID: 0911.2803 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Fourier analysis of the approximation power of principal shift-invariant spaces / rank
 
Normal rank
Property / cites work
 
Property / cites work: Approximation using scattered shifts of a multivariate function / rank
 
Normal rank
Property / cites work
 
Property / cites work: Some Maximal Inequalities / rank
 
Normal rank
Property / cites work
 
Property / cites work: The Runge phenomenon and spatially variable shape parameters in RBF interpolation / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q3531572 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Improved accuracy of multiquadric interpolation using variable shape parameters / rank
 
Normal rank
Property / cites work
 
Property / cites work: Approximation by radial bases and neural networks / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q3135829 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Fast rates for support vector machines using Gaussian kernels / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q3174075 / rank
 
Normal rank

Latest revision as of 23:35, 2 July 2024

scientific article
Language Label Description Also known as
English
Nonlinear approximation using Gaussian kernels
scientific article

    Statements

    Nonlinear approximation using Gaussian kernels (English)
    0 references
    0 references
    0 references
    7 July 2010
    0 references
    The main result of the paper is the following Theorem. Let \(f\) belong to Triebel-Lizorkin space \(F^s_{\tau,q}(\mathbb{R}^d)\) with parameters satisfying \(s> 0\) and \[ {1\over\tau}={1\over p}+{s\over d},\quad {1\over q}= 1+{s\over d} \] for some \(p\in [1,+\infty)\). Then there is a linear combination of \(N\) shifted-dilated Gaussians \[ s_f(x):= \sum^N_{j=1} A_j\exp\Biggl(-\Biggl\|{x- \xi_j\over\sigma_j}\Biggr\|^2\Biggr) \] such that \(\| f- S_f\|_{L_p(\mathbb{R}^d)}\leq C(p,s,d)N^{-s/d}|f|_{F^s_{\tau,q}(\mathbb{R}^d)}\). The same holds for (slightly smaller for these parameters Besov space \(B^s_{\tau,q}(\mathbb{R}^n)\). However, for this case the result holds also for \(p=\infty\).
    0 references
    nonlinear approximation
    0 references
    shifted-dilated Gaussian
    0 references
    Besov space
    0 references
    Triebel-Lizorkin space
    0 references

    Identifiers

    0 references
    0 references
    0 references
    0 references
    0 references
    0 references