Approximation using scattered shifts of a multivariate function ∗ Ronald DeVore and Amos Ron February 19 , 2008
نویسندگان
چکیده
The approximation of a general d-variate function f by the shifts φ(· − ξ), ξ ∈ Ξ ⊂ R d , of a fixed function φ occurs in many applications such as data fitting , neural networks, and learning theory. When Ξ = hZ d is a dilate of the integer lattice, there is a rather complete understanding of the approximation problem [6, 18] using Fourier techniques. However, in most applications the center set Ξ is either given, or can be chosen with complete freedom. In both of these cases, the shift-invariant setting is too restrictive. This paper studies the approximation problem in the case Ξ is arbitrary. It establishes approximation theorems whose error bounds reflect the local density of the points in Ξ. Two different settings are analyzed. The first is when the set Ξ is prescribed in advance. In this case, the theorems of this paper show that, in analogy with the classical univariate spline approximation , improved approximation occurs in regions where the density is high. The second setting corresponds to the problem of non-linear approximation. In that setting the set Ξ can be chosen using information about the target function f. We discuss how to 'best' make these choices and give estimates for the approximation error.
منابع مشابه
Approximation using scattered shifts of a multivariate function
The approximation of a general d-variate function f by the shifts φ(· − ξ), ξ ∈ Ξ ⊂ Rd, of a fixed function φ occurs in many applications such as data fitting, neural networks, and learning theory. When Ξ = hZd is a dilate of the integer lattice, there is a rather complete understanding of the approximation problem [6, 18] using Fourier techniques. However, in most applications the center set Ξ...
متن کاملApproximation from shift - invariant subspaces of L 2 ( IR d )
Abstract: A complete characterization is given of closed shift-invariant subspaces of L2(IR) which provide a specified approximation order. When such a space is principal (i.e., generated by a single function), then this characterization is in terms of the Fourier transform of the generator. As a special case, we obtain the classical Strang-Fix conditions, but without requiring the generating f...
متن کاملThe L 2 - Approximation Orders of Principal Shift - Invariant Spaces Generated by a Radial Basis Function
Approximations from the L 2 -closure S of the nite linear combinations of the shifts of a radial basis function are considered, and a thorough analysis of the least-squares approximation orders from such spaces is provided. The results apply to polyharmonic splines, multiquadrics, the Gaussian kernel and other functions, and include the derivation of spectral orders. For stationary re nements i...
متن کاملOn the Construction of Multivariate (Pre)Wavelets
A new approach for the construction of wavelets and prewavelets on R d from multiresolution is presented. The method uses only properties of shiftinvariant spaces and orthogonal projectors from L2(R d) onto these spaces, and requires neither decay nor stability of the scaling function. Furthermore, this approach allows a simple derivation of previous, as well as new, constructions of wavelets, ...
متن کامل