An overview on deep learning-based approximation methods for partial differential equations

C Beck, M Hutzenthaler, A Jentzen… - arxiv preprint arxiv …, 2020 - arxiv.org
It is one of the most challenging problems in applied mathematics to approximatively solve
high-dimensional partial differential equations (PDEs). Recently, several deep learning …

An extreme learning machine-based method for computational PDEs in higher dimensions

Y Wang, S Dong - Computer Methods in Applied Mechanics and …, 2024 - Elsevier
We present two effective methods for solving high-dimensional partial differential equations
(PDE) based on randomized neural networks. Motivated by the universal approximation …

Approximation bounds for random neural networks and reservoir systems

L Gonon, L Grigoryeva, JP Ortega - The Annals of Applied …, 2023 - projecteuclid.org
This work studies approximation based on single-hidden-layer feedforward and recurrent
neural networks with randomly generated internal weights. These methods, in which only …

Universal approximation theorem and error bounds for quantum neural networks and quantum reservoirs

L Gonon, A Jacquier - arxiv preprint arxiv:2307.12904, 2023 - arxiv.org
Universal approximation theorems are the foundations of classical neural networks,
providing theoretical guarantees that the latter are able to approximate maps of interest …

Deep ReLU neural networks overcome the curse of dimensionality for partial integrodifferential equations

L Gonon, C Schwab - Analysis and Applications, 2023 - World Scientific
Deep neural networks (DNNs) with ReLU activation function are proved to be able to
express viscosity solutions of linear partial integrodifferential equations (PIDEs) on state …

Infinite-dimensional reservoir computing

L Gonon, L Grigoryeva, JP Ortega - Neural Networks, 2024 - Elsevier
Reservoir computing approximation and generalization bounds are proved for a new
concept class of input/output systems that extends the so-called generalized Barron …

Mathematical introduction to deep learning: methods, implementations, and theory

A Jentzen, B Kuckuck, P von Wurstemberger - arxiv preprint arxiv …, 2023 - arxiv.org
This book aims to provide an introduction to the topic of deep learning algorithms. We review
essential components of deep learning algorithms in full mathematical detail including …

Chefs' random tables: Non-trigonometric random features

V Likhosherstov, KM Choromanski… - Advances in …, 2022 - proceedings.neurips.cc
We introduce chefs' random tables (CRTs), a new class of non-trigonometric random
features (RFs) to approximate Gaussian and softmax kernels. CRTs are an alternative to …

Dense-exponential random features: sharp positive estimators of the Gaussian kernel

V Likhosherstov, KM Choromanski… - Advances in …, 2024 - proceedings.neurips.cc
The problem of efficient approximation of a linear operator induced by the Gaussian or
softmax kernel is often addressed using random features (RFs) which yield an unbiased …

[PDF][PDF] Universal approximation property of random neural networks

A Neufeld, P Schmocker - arxiv preprint arxiv:2312.08410, 2023 - researchgate.net
ARIEL NEUFELD AND PHILIPP SCHMOCKER ABSTRACT. In this paper, we study random
neural networks which are single-hidden-layer feedforward neural networks whose weights …