Error bounds for deep ReLU networks using the Kolmogorov-Arnold superposition theorem

DOI10.1016/J.NEUNET.2019.12.013MaRDI QIDQ2055036zbMATH OpenOpenAlexWikidataFDO

Authors Hadrien Montanelli, Haizhao Yang

Publication date 3 December 2021

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1906.11945

zbMATH Keywords

approximation theorycurse of dimensionalitydeep ReLU networksKolmogorov-Arnold superposition theorem

Mathematics Subject Classification ID

Representation and superposition of functions (26B40) Approximation by other special function classes (41A30) Multidimensional problems (41A63) Artificial neural networks and deep learning (68T07)

Recommendations

• New error bounds for deep ReLU networks using sparse grids
• Error bounds for approximations with deep ReLU networks
• Deep ReLU Networks Overcome the Curse of Dimensionality for Generalized Bandlimited Functions
• A note on the expressive power of deep rectified linear unit networks in high-dimensional spaces
• Error bounds for approximations with deep ReLU neural networks in \(W^{s , p}\) norms

Cites work

• An improvement in the superposition theorem of Kolmogorov
• Approximation by superpositions of a sigmoidal function
• Breaking the curse of dimensionality with convex neural networks
• Error bounds for approximations with deep ReLU networks
• scientific article; zbMATH DE number 3117676 (Why is no real title available?)
• scientific article; zbMATH DE number 3147699 (Why is no real title available?)
• scientific article; zbMATH DE number 3147701 (Why is no real title available?)
• scientific article; zbMATH DE number 1928659 (Why is no real title available?)
• scientific article; zbMATH DE number 3274056 (Why is no real title available?)
• Metric Entropy, Widths, and Superpositions of Functions
• Multilayer feedforward networks are universal approximators
• New error bounds for deep ReLU networks using sparse grids
• Numerical Methods for Special Functions
• On a constructive proof of Kolmogorov's superposition theorem
• On the Structure of Continuous Functions of Several Variables
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• Optimal nonlinear approximation
• Provable approximation properties for deep neural networks

Cited in

(42)

• Rademacher complexity and the generalization error of residual networks
• Structure probing neural network deflation
• Machine learning for prediction with missing dynamics
• SelectNet: self-paced learning for high-dimensional partial differential equations
• On sharpness of an error bound for deep ReLU network approximation
• Kolmogorov width decay and poor approximators in machine learning: shallow neural networks, random feature models and neural tangent kernels
• Error bounds for approximations with deep ReLU networks
• Growing axons: greedy learning of neural networks with application to function approximation
• A three layer neural network can represent any multivariate function
• ReLU networks are universal approximators via piecewise linear or constant functions
• Deep network with approximation error being reciprocal of width to power of square root of depth
• New error bounds for deep ReLU networks using sparse grids
• Deep ReLU Networks Overcome the Curse of Dimensionality for Generalized Bandlimited Functions
• The discovery of dynamics via linear multistep methods and deep learning: error estimation
• Error bounds for approximations with deep ReLU neural networks in \(W^{s , p}\) norms
• Deep Network Approximation for Smooth Functions
• Deep network approximation characterized by number of neurons
• Stationary Density Estimation of Itô Diffusions Using Deep Learning
• Simultaneous neural network approximation for smooth functions
• Neural network approximation: three hidden layers are enough
• On the approximation of functions by tanh neural networks
• A note on computing with Kolmogorov superpositions without iterations
• Convergence of deep convolutional neural networks
• The Kolmogorov-Arnold representation theorem revisited
• Friedrichs Learning: Weak Solutions of Partial Differential Equations via Deep Learning
• Deep Neural Networks with ReLU-Sine-Exponential Activations Break Curse of Dimensionality in Approximation on Hölder Class
• Deep nonparametric estimation of intrinsic data structures by chart autoencoders: generalization error and robustness
• Approximation of compositional functions with ReLU neural networks
• Error bounds for deep ReLU networks using the Kolmogorov--Arnold superposition theorem
• Convergence rate of DeepONets for learning operators arising from advection-diffusion equations
• ExSpliNet: An interpretable and expressive spline-based neural network
• Solving PDEs on unknown manifolds with machine learning
• Quasi-interpolation for high-dimensional function approximation
• Optimal linear B-spline approximation via Kolmogorov superposition theorem and its applications
• On the expressivity of the ExSpliNet KAN model
• Analysis of structured deep kernel networks
• Construction of the Kolmogorov-Arnold networks using the Newton-Kaczmarz method
• Structured and balanced multicomponent and multilayer neural networks
• A Kolmogorov high order deep neural network for high frequency partial differential equations in high dimensions
• Identifying stochastic dynamics via finite expression methods
• A Kolmogorov-Arnold neural model for cascading extremes
• Physics informed Kolmogorov-Arnold neural networks for dynamical analysis via efficient-KAN and WAV-KAN

This page was built for publication: Error bounds for deep ReLU networks using the Kolmogorov-Arnold superposition theorem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2055036)