Interpolation of Lipschitz functions

  • Authors:
  • Gleb Beliakov

  • Affiliations:
  • School of Information Technology, Deakin University, Burwood, Australia

  • Venue:
  • Journal of Computational and Applied Mathematics
  • Year:
  • 2006

Quantified Score

Hi-index 7.29

Visualization

Abstract

This paper describes a new computational approach to multivariate scattered data interpolation. It is assumed that the data is generated by a Lipschitz continuous function f. The proposed approach uses the central interpolation scheme, which produces an optimal interpolant in the worst case scenario. It provides best uniform error bounds on f, and thus translates into reliable learning of f. This paper develops a computationally efficient algorithm for evaluating the interpolant in the multivariate case. We compare the proposed method with the radial basis functions and natural neighbor interpolation, provide the details of the algorithm and illustrate it on numerical experiments. The efficiency of this method surpasses alternative interpolation methods for scattered data.