Learning and approximation by Gaussians on Riemannian manifolds

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

29 Scopus Citations
View graph of relations

Author(s)

  • Gui-Bo Ye
  • Ding-Xuan Zhou

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)291-310
Journal / PublicationAdvances in Computational Mathematics
Volume29
Issue number3
Publication statusPublished - Oct 2008

Abstract

Learning function relations or understanding structures of data lying in manifolds embedded in huge dimensional Euclidean spaces is an important topic in learning theory. In this paper we study the approximation and learning by Gaussians of functions defined on a d-dimensional connected compact C Riemannian submanifold of IRn which is isometrically embedded. We show that the convolution with the Gaussian kernel with variance σ provides the uniform approximation order of O(σs) when the approximated function is Lipschitz s ∈ (0, 1]. The uniform normal neighborhoods of a compact Riemannian manifold play a central role in deriving the approximation order. This approximation result is used to investigate the regression learning algorithm generated by the multi-kernel least square regularization scheme associated with Gaussian kernels with flexible variances. When the regression function is Lipschitz s, our learning rate is (log2 m)/m)s/(8 s + 4 d) where m is the sample size. When the manifold dimension d is smaller than the dimension n of the underlying Euclidean space, this rate is much faster compared with those in the literature. By comparing approximation orders, we also show the essential difference between approximation schemes with flexible variances and those with a single variance. © 2007 Springer Science+Business Media, Inc.

Research Area(s)

  • Approximation, Gaussian kernels, Learning theory, Multi-kernel least square regularization scheme, Reproducing kernel Hilbert spaces, Riemannian manifolds

Citation Format(s)

Learning and approximation by Gaussians on Riemannian manifolds. / Ye, Gui-Bo; Zhou, Ding-Xuan.
In: Advances in Computational Mathematics, Vol. 29, No. 3, 10.2008, p. 291-310.

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review