On best approximation of classes by radial functions

We investigate the radial manifolds Rn, generated by a linear combination of n radial functions on Rd. We consider the best approximation of function classes by the manifold Rn. In particular, we prove that the deviation of the manifold Rn from the Sobolev class W2r,d in the Hilbert space L2 behaves asymptotically as n-r/d-1. We show the connection between the manifold Rn and the space of algebraic polynomials Pd,s of degree s. Namely, we prove there exist constants c1 and c2 such that the space Pd,s is either contained or not in Rn as n ≥ c1sd-1 or n ≤ c2sd-1, respectively.

[1]  G. Szegő Zeros of orthogonal polynomials , 1939 .

[2]  E. Stein,et al.  Introduction to Fourier Analysis on Euclidean Spaces. , 1971 .

[3]  Sankatha Prasad Singh,et al.  Approximation Theory, Spline Functions and Applications , 1992 .

[4]  Allan Pinkus,et al.  Lower bounds for approximation by MLP neural networks , 1999, Neurocomputing.

[5]  Joel Ratsaby,et al.  The Degree of Approximation of Sets in Euclidean Space Using Sets with Bounded Vapnik-Chervonenkis Dimension , 1998, Discret. Appl. Math..

[6]  C. Micchelli,et al.  Approximation by superposition of sigmoidal and radial basis functions , 1992 .

[7]  Carlos A. Berenstein,et al.  Approximation by spherical waves inLp-spaces , 1996 .

[8]  Allan Pinkus Approximating by Ridge Functions , 1997 .

[9]  Robert Schaback,et al.  Approximation by radial basis functions with finitely many centers , 1996 .

[10]  Allan Pinkus,et al.  On a recovery problem , 1995 .

[11]  R. DeVore,et al.  Optimal nonlinear approximation , 1989 .

[12]  George G. Lorentz,et al.  Constructive Approximation , 1993, Grundlehren der mathematischen Wissenschaften.

[13]  Eric Todd Quinto,et al.  Injectivity Sets for the Radon Transform over Circles and Complete Systems of Radial Functions , 1996 .

[14]  J. Milnor On the Betti numbers of real varieties , 1964 .

[15]  A. Pinkus,et al.  Approximation of Multivariate Functions , 2004 .

[16]  Allan Pinkus,et al.  Approximation theory of the MLP model in neural networks , 1999, Acta Numerica.

[17]  Allan Pinkus,et al.  Some Density Problems in Multivariate Approximation , 2004 .

[18]  Andrew D. Back,et al.  Radial Basis Functions , 2001 .

[19]  A. Pinkus,et al.  Fundamentality of Ridge Functions , 1993 .

[20]  G. Andrews,et al.  Classical orthogonal polynomials , 1985 .

[21]  C. Bennett,et al.  Interpolation of operators , 1987 .

[22]  B. Logan,et al.  Optimal reconstruction of a function from its projections , 1975 .

[23]  A. Pinkus TDI-Subspaces ofC(Rd) and Some Density Problems from Neural Networks , 1996 .

[24]  Joel Ratsaby,et al.  On the Degree of Approximation by Manifolds of Finite Pseudo-Dimension , 1999 .

[25]  Martin D. Buhmann,et al.  Radial Basis Functions , 2021, Encyclopedia of Mathematical Geosciences.

[26]  Andrew R. Barron,et al.  Universal approximation bounds for superpositions of a sigmoidal function , 1993, IEEE Trans. Inf. Theory.

[27]  D. Levin,et al.  On quasi-interpolation by radial basis functions with scattered centres , 1995 .

[28]  P. Petrushev Approximation by ridge functions and neural networks , 1999 .

[29]  George G. Lorentz,et al.  Problems in approximation theory , 1977 .

[30]  A. Bejancu,et al.  ON THE ACCURACY OF SURFACE SPLINE APPROXIMATION AND INTERPOLATION TO BUMP FUNCTIONS , 2001, Proceedings of the Edinburgh Mathematical Society.

[31]  G. Lorentz,et al.  Constructive approximation : advanced problems , 1996 .

[32]  A. Pinkus,et al.  Identifying Linear Combinations of Ridge Functions , 1999 .

[33]  W. Light Some Aspects of Radial Basis Function Approximation , 1992 .

[34]  Vitaly Maiorov,et al.  On the Best Approximation by Ridge Functions in the Uniform Norm , 2001 .

[35]  H. N. Mhaskar,et al.  Neural Networks for Optimal Approximation of Smooth and Analytic Functions , 1996, Neural Computation.

[36]  P. Heywood Trigonometric Series , 1968, Nature.

[37]  V. Maiorov On Best Approximation by Ridge Functions , 1999 .

[38]  Robert Schaback,et al.  Error estimates and condition numbers for radial basis function interpolation , 1995, Adv. Comput. Math..

[39]  Ron Meir,et al.  On the near optimality of the stochastic approximation of smooth functions by neural networks , 2000, Adv. Comput. Math..

[40]  Hrushikesh Narhar Mhaskar,et al.  Approximation properties of zonal function networks using scattered data on the sphere , 1999, Adv. Comput. Math..

[41]  N. Vilenkin Special Functions and the Theory of Group Representations , 1968 .

[42]  Y. Makovoz Random Approximants and Neural Networks , 1996 .

[43]  R. Meir,et al.  On the Approximation of Functional Classes Equipped with a Uniform Measure Using Ridge Functions , 1999 .