English

Smooth function approximation by deep neural networks with general activation functions

Machine Learning 2019-07-24 v2 Machine Learning

Abstract

There has been a growing interest in expressivity of deep neural networks. However, most of the existing work about this topic focuses only on the specific activation function such as ReLU or sigmoid. In this paper, we investigate the approximation ability of deep neural networks with a broad class of activation functions. This class of activation functions includes most of frequently used activation functions. We derive the required depth, width and sparsity of a deep neural network to approximate any H\"older smooth function upto a given approximation error for the large class of activation functions. Based on our approximation error analysis, we derive the minimax optimality of the deep neural network estimators with the general activation functions in both regression and classification problems.

Keywords

Cite

@article{arxiv.1906.06903,
  title  = {Smooth function approximation by deep neural networks with general activation functions},
  author = {Ilsang Ohn and Yongdai Kim},
  journal= {arXiv preprint arXiv:1906.06903},
  year   = {2019}
}

Comments

24 pages

R2 v1 2026-06-23T09:55:20.094Z