English

Deep ReLU network approximation of functions on a manifold

Machine Learning 2019-08-05 v1 Machine Learning

Abstract

Whereas recovery of the manifold from data is a well-studied topic, approximation rates for functions defined on manifolds are less known. In this work, we study a regression problem with inputs on a dd^*-dimensional manifold that is embedded into a space with potentially much larger ambient dimension. It is shown that sparsely connected deep ReLU networks can approximate a H\"older function with smoothness index β\beta up to error ϵ\epsilon using of the order of ϵd/βlog(1/ϵ)\epsilon^{-d^*/\beta}\log(1/\epsilon) many non-zero network parameters. As an application, we derive statistical convergence rates for the estimator minimizing the empirical risk over all possible choices of bounded network parameters.

Keywords

Cite

@article{arxiv.1908.00695,
  title  = {Deep ReLU network approximation of functions on a manifold},
  author = {Johannes Schmidt-Hieber},
  journal= {arXiv preprint arXiv:1908.00695},
  year   = {2019}
}
R2 v1 2026-06-23T10:37:54.505Z