A priori estimates for classification problems using neural networks
Machine Learning
2020-09-29 v1 Machine Learning
Numerical Analysis
Numerical Analysis
Abstract
We consider binary and multi-class classification problems using hypothesis classes of neural networks. For a given hypothesis class, we use Rademacher complexity estimates and direct approximation theorems to obtain a priori error estimates for regularized loss functionals.
Cite
@article{arxiv.2009.13500,
title = {A priori estimates for classification problems using neural networks},
author = {Weinan E and Stephan Wojtowytsch},
journal= {arXiv preprint arXiv:2009.13500},
year = {2020}
}