Approximation Capabilities of Feedforward Neural Networks with GELU Activations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yakovlev, Konstantin, Puchkin, Nikita
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915694213332992
author Yakovlev, Konstantin
Puchkin, Nikita
author_facet Yakovlev, Konstantin
Puchkin, Nikita
contents We derive an approximation error bound that holds simultaneously for a function and all its derivatives up to any prescribed order. The bounds apply to elementary functions, including multivariate polynomials, the exponential function, and the reciprocal function, and are obtained using feedforward neural networks with the Gaussian Error Linear Unit (GELU) activation. In addition, we report the network size, weight magnitudes, and behavior at infinity. Our analysis begins with a constructive approximation of multiplication, where we prove the simultaneous validity of error bounds over domains of increasing size for a given approximator. Leveraging this result, we obtain approximation guarantees for division and the exponential function, ensuring that all higher-order derivatives of the resulting approximators remain globally bounded.
format Preprint
id arxiv_https___arxiv_org_abs_2512_21749
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Approximation Capabilities of Feedforward Neural Networks with GELU Activations
Yakovlev, Konstantin
Puchkin, Nikita
Machine Learning
We derive an approximation error bound that holds simultaneously for a function and all its derivatives up to any prescribed order. The bounds apply to elementary functions, including multivariate polynomials, the exponential function, and the reciprocal function, and are obtained using feedforward neural networks with the Gaussian Error Linear Unit (GELU) activation. In addition, we report the network size, weight magnitudes, and behavior at infinity. Our analysis begins with a constructive approximation of multiplication, where we prove the simultaneous validity of error bounds over domains of increasing size for a given approximator. Leveraging this result, we obtain approximation guarantees for division and the exponential function, ensuring that all higher-order derivatives of the resulting approximators remain globally bounded.
title Approximation Capabilities of Feedforward Neural Networks with GELU Activations
topic Machine Learning
url https://arxiv.org/abs/2512.21749