Approximation bounds for norm constrained neural networks with applications to regression and GANs

DOI10.1016/j.acha.2023.03.004zbMath1528.41035arXiv2201.09418MaRDI QIDQ6038825

Yu Ling Jiao, Yang Wang, Yunfei Yang

Publication date: 3 May 2023

Published in: Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2201.09418

zbMATH Keywords

neural networkapproximation theorydeep learningGAN

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Artificial neural networks and deep learning (68T07) Rate of convergence, degree of approximation (41A25)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• On the degree of approximation by manifolds of finite pseudo-dimension
• High-dimensional distribution generation through deep neural networks
• Loss landscapes and optimization in over-parameterized non-linear systems and neural networks
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• Nonparametric regression using deep neural networks with ReLU activation function
• Error bounds for approximations with deep ReLU networks
• The best constants in the Khintchine inequality
• Universal approximation bounds for superpositions of a sigmoidal function
• Integral Probability Metrics and Their Generating Classes of Functions
• The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network
• High-Dimensional Probability
• 10.1162/153244303321897690
• Size-independent sample complexity of neural networks
• Optimal Approximation with Sparsely Connected Deep Neural Networks
• Deep ReLU Networks Overcome the Curse of Dimensionality for Generalized Bandlimited Functions
• Deep Network Approximation for Smooth Functions
• Deep Network Approximation Characterized by Number of Neurons
• Understanding Machine Learning
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Approximation by superpositions of a sigmoidal function
• On the capacity of deep generative networks for approximating distributions
• The Kolmogorov-Arnold representation theorem revisited