Approximation of Functions.

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.