English

Deep ReLU neural networks in high-dimensional approximation

Numerical Analysis 2021-07-26 v2 Numerical Analysis

Abstract

We study the computation complexity of deep ReLU (Rectified Linear Unit) neural networks for the approximation of functions from the H\"older-Zygmund space of mixed smoothness defined on the dd-dimensional unit cube when the dimension dd may be very large. The approximation error is measured in the norm of isotropic Sobolev space. For every function ff from the H\"older-Zygmund space of mixed smoothness, we explicitly construct a deep ReLU neural network having an output that approximates ff with a prescribed accuracy ε\varepsilon, and prove tight dimension-dependent upper and lower bounds of the computation complexity of this approximation, characterized as the size and the depth of this deep ReLU neural network, explicitly in dd and ε\varepsilon. The proof of these results are in particular, relied on the approximation by sparse-grid sampling recovery based on the Faber series.

Keywords

Cite

@article{arxiv.2007.08729,
  title  = {Deep ReLU neural networks in high-dimensional approximation},
  author = {Dinh Dũng and Van Kien Nguyen},
  journal= {arXiv preprint arXiv:2007.08729},
  year   = {2021}
}

Comments

5 figures

R2 v1 2026-06-23T17:11:09.012Z