Approximation of Smoothness Classes by Deep Rectifier Networks
From MaRDI portal
Publication:5020751
DOI10.1137/20M1360657zbMath1494.41008arXiv2007.15645MaRDI QIDQ5020751
Publication date: 7 January 2022
Published in: SIAM Journal on Numerical Analysis (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2007.15645
Numerical computation using splines (65D07) Artificial neural networks and deep learning (68T07) Spline approximation (41A15) Approximation by other special function classes (41A30)
Related Items (5)
Neural network approximation ⋮ Deep ReLU neural network approximation in Bochner spaces and applications to parametric PDEs ⋮ Approximation theory of tree tensor networks: tensorized univariate functions ⋮ Extracting a function encoded in amplitudes of a quantum state by tensor network and orthogonal function expansion ⋮ Collocation approximation by deep neural ReLU networks for parametric and stochastic PDEs with lognormal inputs
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Quasiconformal mappings and extendability of functions in Sobolev spaces
- Optimal nonlinear approximation
- Wavelet coefficients measuring smoothness in \(H_ p(\mathbb{R}^ d)\)
- Optimal approximation of piecewise smooth functions using deep ReLU neural networks
- Error bounds for approximations with deep ReLU networks
- \(H^p\) spaces of several variables
- Maximal functions measuring smoothness
- Biorthogonal bases of compactly supported wavelets
- Besov Spaces on Domains in ℝ d
- Orthogonal Polynomials and the Construction of Piecewise Polynomial Smooth Wavelets
- On nonlinear 𝑛-widths
- Optimal Approximation with Sparsely Connected Deep Neural Networks
- Deep ReLU networks and high-order finite element methods
This page was built for publication: Approximation of Smoothness Classes by Deep Rectifier Networks
