Nonlinear Weighted Directed Acyclic Graph and A Priori Estimates for Neural Networks

DOI10.1137/21M140955XzbMath1491.68184arXiv2103.16355OpenAlexW3144724655MaRDI QIDQ5081927

Chao Ma, Tao Luo, Yu-Qing Li

Publication date: 17 June 2022

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2103.16355

zbMATH Keywords

a priori estimatesadjacency matrixDenseNetnonlinear weighted directed acyclic graph

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Small world graphs, complex networks (graph-theoretic aspects) (05C82) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46)

Cites Work

• Rademacher complexity and the generalization error of residual networks
• Representation formulas and pointwise properties for Barron functions
• Kolmogorov width decay and poor approximators in machine learning: shallow neural networks, random feature models and neural tangent kernels
• A priori estimates of the population risk for two-layer neural networks
• Size-independent sample complexity of neural networks
• Spurious Valleys in Two-layer Neural Network Optimization Landscapes
• Understanding Machine Learning