New error bounds for deep networks using sparse grids
Numerical Analysis
2018-08-15 v3
Abstract
We prove a theorem concerning the approximation of multivariate functions by deep ReLU networks. We present new error estimates for which the curse of the dimensionality is lessened by establishing a connection with sparse grids.
Cite
@article{arxiv.1712.08688,
title = {New error bounds for deep networks using sparse grids},
author = {Hadrien Montanelli and Qiang Du},
journal= {arXiv preprint arXiv:1712.08688},
year = {2018}
}