Exponential Convergence of the Deep Neural Network Approximation for Analytic Functions

2018/07/01 by E Weinan, E, Weinan, Qingcan Wang +1 · 4 citations
Computer Science · Physics and Astronomy · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Matrix Theory and Algorithms #Model Reduction and Neural Networks #Neural Networks and Applications

paper · pdf · doi:10.48550/arxiv.1807.00297

openalex publication_date 2018/07/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We prove that for analytic functions in low dimension, the convergence rate of the deep neural network approximation is exponential.

Citations

• Benefits of depth in neural networks
• The Expressive Power of Neural Networks: A View from the Width

Cited by

• One model to solve them all: 2BSDE families via neural operators
• General transformation neural networks: A class of parametrized functions for high-dimensional function approximation
• Spectral connvergece of random feature method in one dimension
• Sharp uniform approximation for spectral Barron functions by deep neural networks

Related

• Deep Neural Network Approximation Theory
• Optimal Approximation Complexity of High-Dimensional Functions with Neural Networks
• Deep Learning in High Dimension: Neural Network Approximation of Analytic Functions in L²(ℝ^d,γ_d)
• Deep neural network approximation theory for high-dimensional functions
• Why Deep Neural Networks for Function Approximation?