Approximation and gradient descent training with neural networks

DOI10.1007/S43670-025-00116-1MaRDI QIDQ6865648zbMATH OpenFDO

Authors Gerrit Welper

Publication date 2 February 2026

Published in Sampling Theory, Signal Processing, and Data Analysis (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S43670-025-00116-1

zbMATH Keywords

approximationdeep neural networksgradient descentneural tangent kernel

Mathematics Subject Classification ID

Approximation by arbitrary nonlinear expressions; widths and entropy (41A46) Numerical optimization and variational techniques (65K10) Artificial neural networks and deep learning (68T07)

Cites work

• Approximation by Combinations of ReLU and Squared ReLU Ridge Functions With <inline-formula> <tex-math notation="LaTeX">$\ell^1$ </tex-math> </inline-formula> and <inline-formula>
• Approximation rates for neural networks with general activation functions
• Approximation results for gradient flow trained neural networks
• Approximation spaces of deep neural networks
• Better approximations of high dimensional smooth functions by deep neural networks with rectified power units
• Breaking the curse of dimensionality with convex neural networks
• Constructive deep ReLU neural network approximation
• Deep Network Approximation for Smooth Functions
• Deep ReLU networks and high-order finite element methods
• Error bounds for approximations with deep ReLU networks
• Error bounds for approximations with deep ReLU neural networks in \(W^{s , p}\) norms
• Gradient descent optimizes over-parameterized deep ReLU networks
• Greedy training algorithms for neural networks and applications to PDEs
• High-dimensional probability. An introduction with applications in data science
• High-order approximation rates for shallow neural networks with cosine and \(\mathrm{ReLU}^k\) activation functions
• scientific article; zbMATH DE number 1215245 (Why is no real title available?)
• scientific article; zbMATH DE number 1405266 (Why is no real title available?)
• Neural network approximation
• Nonlinear approximation and (deep) ReLU networks
• Nonlinear approximation via compositions
• Optimal Convergence Rates for the Orthogonal Greedy Algorithm
• The Barron space and the flow-induced function spaces for neural network models
• The gap between theory and practice in function approximation with deep neural networks
• The Modern Mathematics of Deep Learning
• Towards a mathematical understanding of neural network-based machine learning: what we know and what we don't

This page was built for publication: Approximation and gradient descent training with neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6865648)