Neural network approximation

DOI10.1017/S0962492921000052MaRDI QIDQ5887830

Guergana Petrova, Boris Hanin, Ronald A. DeVore

Publication date: 14 April 2023

Published in: Acta Numerica (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2012.14501

Mathematics Subject Classification ID

Fluid mechanics (76-XX) Numerical analysis (65-XX)

Related Items (29)

Sparse Deep Neural Network for Nonlinear Partial Differential Equations ⋮ Turnpike in optimal control of PDEs, ResNets, and beyond ⋮ WARPd: A Linearly Convergent First-Order Primal-Dual Algorithm for Inverse Problems with Approximate Sharpness Conditions ⋮ Two-Layer Neural Networks with Values in a Banach Space ⋮ Discretization of parameter identification in PDEs using neural networks ⋮ Simultaneous neural network approximation for smooth functions ⋮ Deep ReLU neural network approximation in Bochner spaces and applications to parametric PDEs ⋮ Deep learning methods for partial differential equations and related parameter identification problems ⋮ Learning-informed parameter identification in nonlinear time-dependent PDEs ⋮ Neural network representation of time integrators ⋮ Solving Elliptic Problems with Singular Sources Using Singularity Splitting Deep Ritz Method ⋮ Data-driven vortex solitons and parameter discovery of 2D generalized nonlinear Schrödinger equations with a \(\mathcal{PT}\)-symmetric optical lattice ⋮ Knowledge-informed neuro-integrators for aggregation kinetics ⋮ Random neural networks in the infinite width limit as Gaussian processes ⋮ Deep neural networks learning forward and inverse problems of two-dimensional nonlinear wave equations with rational solitons ⋮ A multivariate Riesz basis of ReLU neural networks ⋮ Collocation approximation by deep neural ReLU networks for parametric and stochastic PDEs with lognormal inputs ⋮ An endeavor from the Glowinski-Le Tallec splitting for approximating the solution of Kawarada equation ⋮ Optimal learning ⋮ A Scalable Deep Learning Approach for Solving High-Dimensional Dynamic Optimal Transport ⋮ Error assessment of an adaptive finite elements -- neural networks method for an elliptic parametric PDE ⋮ Greedy training algorithms for neural networks and applications to PDEs ⋮ Sobolev-type embeddings for neural network approximation spaces ⋮ Approximation with one-bit polynomials in Bernstein form ⋮ Lipschitz widths ⋮ Stable recovery of entangled weights: towards robust identification of deep neural networks from minimal samples ⋮ Information theory and recovery algorithms for data fusion in Earth observation ⋮ Spline representation and redundancies of one-dimensional ReLU neural network models ⋮ A New Function Space from Barron Class and Application to Neural Network Approximation

Uses Software

• ImageNet
• GNMT

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Approximation of functions of few variables in high dimensions
• Interpolation of linear operators on Sobolev spaces
• Entropy numbers, s-numbers, and eigenvalue problems
• A practical guide to splines
• On best approximation by ridge functions
• Approximation and estimation bounds for artificial neural networks
• Multilayer feedforward networks are universal approximators
• Optimal nonlinear approximation
• Wavelet compression and nonlinear \(n\)-widths
• Random approximants and neural networks
• Some remarks on greedy algorithms
• Exponential convergence of the deep neural network approximation for analytic functions
• Linearized two-layers neural networks in high dimension
• Nonlinear approximation and (deep) ReLU networks
• Approximation spaces of deep neural networks
• Exponential ReLU DNN expression of holomorphic maps in high dimension
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• Nonlinear approximation via compositions
• Function approximation by deep networks
• Nonparametric regression using deep neural networks with ReLU activation function
• A unifying representer theorem for inverse problems and machine learning
• Error bounds for approximations with deep ReLU networks
• Greedy algorithms for reduced bases in Banach spaces
• Optimal stable nonlinear approximation
• A prioriconvergence of the Greedy algorithm for the parametrized reduced basis method
• Convergence Rates for Greedy Algorithms in Reduced Basis Methods
• Theory of Classification: a Survey of Some Recent Advances
• Relu Deep Neural Networks and Linear Finite Elements
• Interpolation of Besov Spaces
• Besov Spaces on Domains in ℝ d
• Facing up to arrangements: face-count formulas for partitions of space by hyperplanes
• Approximation by Ridge Functions and Neural Networks
• Universal approximation bounds for superpositions of a sigmoidal function
• 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
• Deep Neural Network Approximation Theory
• Approximation of Smoothness Classes by Deep Rectifier Networks
• Optimal Approximation with Sparsely Connected Deep Neural Networks
• Benign overfitting in linear regression
• Deep ReLU networks and high-order finite element methods
• Deep Network Approximation for Smooth Functions
• Data Assimilation in Reduced Modeling
• Breaking the Curse of Dimensionality with Convex Neural Networks
• Expressivity of Deep Neural Networks
• Approximation by superpositions of a sigmoidal function

This page was built for publication: Neural network approximation