A New Function Space from Barron Class and Application to Neural Network Approximation

Artificial neural networks and deep learning (68T07) Boundary value problems for second-order elliptic equations (35J25) Finite element, Rayleigh-Ritz and Galerkin methods for boundary value problems involving PDEs (65N30) Stability and convergence of numerical methods for initial value and initial-boundary value problems involving PDEs (65M12) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46)

Cites Work

Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Growth and integrability of Fourier transforms on Euclidean space
Global well-posedness for Keller-Segel system in Besov type spaces
Theory of function spaces
Symétrie et compacité dans les espaces de Sobolev
A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
Approximation by superposition of sigmoidal and radial basis functions
Existence of solitary waves in higher dimensions
Uniform approximation by neural networks
Generalization bounds for function approximation from scattered noisy data
Rates of convex approximation in non-Hilbert spaces
On Gagliardo-Nirenberg type inequalities in Fourier-Herz spaces
Provable approximation properties for deep neural networks
Approximation rates for neural networks with general activation functions
Representation formulas and pointwise properties for Barron functions
Approximation spaces of deep neural networks
The Barron space and the flow-induced function spaces for neural network models
High-order approximation rates for shallow neural networks with cosine and $\mathrm{ReLU}^k$ activation functions
On dispersive effect of the Coriolis force for the stationary Navier-Stokes equations
Optimal constants in the Marcinkiewicz-Zygmund inequalities
Approximation and learning by greedy algorithms
Growth properties of the Fourier transform
Cube Slicing in R n
The best constants in the Khintchine inequality
Approximation by Ridge Functions and Neural Networks
Universal approximation bounds for superpositions of a sigmoidal function
Hinging hyperplanes for regression, classification, and function approximation
Degree of Approximation Results for Feedforward Networks Approximating Unknown Mappings and Their Derivatives
Estimates of Fourier transforms in Sobolev spaces
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> <tex-math notation="LaTeX">$\ell^0$ </tex-math> </inline-formula> Controls
Convergence Rate Analysis for Deep Ritz Method
A Rate of Convergence of Physics Informed Neural Networks for the Linear Second Order Elliptic PDEs
Deep Network Approximation Characterized by Number of Neurons
Deep Nitsche Method: Deep Ritz Method with Essential Boundary Conditions
Global mild solutions of Navier‐Stokes equations
Upper bound on √x J_ν(x) and its applications
On the Theory of Dynamic Programming
Neural network approximation
Ridge functions and orthonormal ridgelets

This page was built for publication: A New Function Space from Barron Class and Application to Neural Network Approximation