Emergent Mind

Approximation in shift-invariant spaces with deep ReLU neural networks

(2005.11949)
Published May 25, 2020 in cs.LG , cs.NA , math.NA , and stat.ML

Abstract

We study the expressive power of deep ReLU neural networks for approximating functions in dilated shift-invariant spaces, which are widely used in signal processing, image processing, communications and so on. Approximation error bounds are estimated with respect to the width and depth of neural networks. The network construction is based on the bit extraction and data-fitting capacity of deep neural networks. As applications of our main results, the approximation rates of classical function spaces such as Sobolev spaces and Besov spaces are obtained. We also give lower bounds of the $Lp (1\le p \le \infty)$ approximation error for Sobolev spaces, which show that our construction of neural network is asymptotically optimal up to a logarithmic factor.

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.

Newsletter

Get summaries of trending comp sci papers delivered straight to your inbox:

Unsubscribe anytime.