New error bounds for deep networks using sparse grids

DOI10.1137/18M1189336MaRDI QIDQ6295641arXivFDO

Authors Hadrien Montanelli, Qiang Du

Publication date 22 December 2017

Published in arXiv

Full work available at URL https://doi.org/10.1137/18M1189336

Mathematics Subject Classification ID

Multidimensional problems (41A63) Artificial neural networks and deep learning (68T07)

arXiv classification

math.NA

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.

Cited in

(1)

• Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width

This page was built for publication: New error bounds for deep networks using sparse grids

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6295641)