Approximation in $L^p(\mu)$ with deep ReLU neural networks
Abstract
We discuss the expressive power of neural networks which use the non-smooth ReLU activation function by analyzing the approximation theoretic properties of such networks. The existing results mainly fall into two categories: approximation using ReLU networks with a fixed depth, or using ReLU networks whose depth increases with the approximation accuracy. After reviewing these findings, we show that the results concerning networks with fixed depth--- which up to now only consider approximation in for the Lebesgue measure --- can be generalized to approximation in , for any finite Borel measure . In particular, the generalized results apply in the usual setting of statistical learning theory, where one is interested in approximation in , with the probability measure describing the distribution of the data.
Keywords
Cite
@article{arxiv.1904.04789,
title = {Approximation in $L^p(\mu)$ with deep ReLU neural networks},
author = {Felix Voigtlaender and Philipp Petersen},
journal= {arXiv preprint arXiv:1904.04789},
year = {2019}
}
Comments
Accepted for presentation at SampTA 2019