Lipschitz widths

DOI10.1007/S00365-022-09576-3MaRDI QIDQ6381931arXivWikidataFDO

Authors Guergana Petrova, P. Wojtaszczyk

Publication date 1 November 2021

Published in arXiv

Full work available at URL https://doi.org/10.1007/S00365-022-09576-3

Mathematics Subject Classification ID

Approximation by arbitrary nonlinear expressions; widths and entropy (41A46) Abstract approximation theory (approximation in normed linear spaces and other abstract spaces) (41A65) Neural nets applied to problems in time-dependent statistical mechanics (82C32)

arXiv classification

cs.NAmath.NA

Abstract: This paper introduces a measure, called Lipschitz widths, of the optimal performance possible of certain nonlinear methods of approximation. It discusses their relation to entropy numbers and other well known widths such as the Kolmogorov and the stable manifold widths. It also shows that the Lipschitz widths provide a theoretical benchmark for the approximation quality achieved via deep neural networks.

This page was built for publication: Lipschitz widths

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6381931)