Exponential expressivity of ${\rm ReLU}^k$ neural networks on Gevrey classes with point singularities


METADATA ONLY
Loading...

Date

2024-03

Publication Type

Report

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

We analyze deep Neural Network emulation rates of smooth functions with point singularities in bounded, polytopal domains \(\mathrm{D} \subset \mathbb{R}^d\), \(d=2,3\). We prove exponential emulation rates in Sobolev spaces in terms of the number of neurons and in terms of the number of nonzero coefficients for Gevrey-regular solution classes defined in terms of weighted Sobolev scales in \(\mathrm{D}\), comprising the countably-normed spaces of I.M. Babu\v{s}ka and B.Q. Guo. As intermediate result, we prove that continuous, piecewise polynomial high order (``\(p\)-version'') finite elements with elementwise polynomial degree \(p\in\mathbb{N}\) on arbitrary, regular, simplicial partitions of polyhedral domains \(\mathrm{D} \subset \mathbb{R}^d\), \(d\geq 2\) can be \emph{exactly emulated} by neural networks combining ReLU and ReLU\(^2\) activations. On shape-regular, simplicial partitions of polytopal domains \(\mathrm{D}\), both the number of neurons and the number of nonzero parameters are proportional to the number of degrees of freedom of the finite element space, in particular for the \(hp\)-Finite Element Method of I.M. Babu\v{s}ka and B.Q. Guo.

Publication status

published

Editor

Book title

Volume

2024-11

Pages / Article No.

Publisher

Seminar for Applied Mathematics, ETH Zurich

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Neural networks; hp-finite element method; Singularities; Gevrey regularity; Exponential convergence

Organisational unit

03435 - Schwab, Christoph / Schwab, Christoph check_circle

Notes

Funding

Related publications and datasets

Is previous version of: