Emergent Mind
Deep ReLU networks overcome the curse of dimensionality for bandlimited functions
(1903.00735)
Published Mar 2, 2019
in
math.NA
and
cs.NA
Abstract
We prove a theorem concerning the approximation of bandlimited multivariate functions by deep ReLU networks for which the curse of the dimensionality is overcome. Our theorem is based on a result by Maurey and on the ability of deep ReLU networks to approximate Chebyshev polynomials and analytic functions efficiently.
We're not able to analyze this paper right now due to high demand.
Please check back later (sorry!).
Generate a summary of this paper on our Pro plan:
We ran into a problem analyzing this paper.