Files
myWiki/raw/papers/schmocker-weighted-uat-2026.md

2.0 KiB

title, source_url, ingested, sha256
title source_url ingested sha256
Weighted Universal Approximation of Differentiable Maps on Infinite-Dimensional Manifolds https://arxiv.org/abs/2606.09820 2026-06-17 <computed>

Weighted Universal Approximation of Differentiable Maps on Infinite-Dimensional Manifolds

Authors: Philipp Schmocker, Josef Teichmann

arXiv: 2606.09820v1 [math.FA] (2026-06-08)

Keywords: Machine learning, neural operator, Universal approximation, weighted approximation, infinite-dimensional manifold, locally convex topological vector space, bounded approximation property, Stone-Weierstrass theorem, Nachbin theorem, Tauberian theorem, non-anticipative functional, rough path, signature.

Abstract

Generalizes the universal approximation theorem for functional input neural networks (FNN) to differentiable maps by including the approximation of the derivatives. A FNN maps the input from a possibly infinite-dimensional weighted manifold to the real-valued hidden layer, on which a non-linear scalar activation function is applied, and then returns the output into a Banach space via some linear readouts. By proving a weighted Nachbin theorem, establishes a universal approximation theorem (UAT) for differentiable maps, which goes beyond the usual formulation on compact sets and also includes the approximation of the derivatives. Leads to approximation results for non-anticipative functionals including the horizontal and vertical derivatives. Also shows that linear functions of the signature are able to approximate path space functionals including their directional derivatives.

Key Concepts