Low dimensional approximation and generalization of multivariate functions on smooth manifolds using deep ReLU neural networks

DOI10.1016/J.NEUNET.2024.106223MaRDI QIDQ6536393zbMATH OpenFDO

Authors Demetrio Labate, Ji Shi

Publication date 25 April 2024

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.NEUNET.2024.106223

zbMATH Keywords

approximation powerapproximation theorydeep learningdeep neural networkgeneralization analysisHölder continuitymanifold learning

Mathematics Subject Classification ID

Approximations and expansions (41Axx) Artificial neural networks and deep learning (68T07)

Recommendations

• Nonparametric regression on low-dimensional manifolds using deep ReLU networks: function approximation and statistical recovery
• Provable approximation properties for deep neural networks
• Deep ReLU neural networks in high-dimensional approximation
• 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

Cites work

• A deep network construction that adapts to intrinsic dimensionality beyond the domain
• A Proof that Artificial Neural Networks Overcome the Curse of Dimensionality in the Numerical Approximation of Black–Scholes Partial Differential Equations
• Adaptive approximation and generalization of deep neural network with intrinsic dimensionality
• Approximation of infinitely differentiable multivariate functions is intractable
• Deep network approximation characterized by number of neurons
• Deep Network Approximation for Smooth Functions
• Deep nonparametric regression on approximate manifolds: nonasymptotic error bounds with polynomial prefactors
• Deep ReLU neural networks in high-dimensional approximation
• Diffusion wavelets
• Error bounds for approximations with deep ReLU networks
• Finding the homology of submanifolds with high confidence from random samples
• High-dimensional probability. An introduction with applications in data science
• Mathematical Foundations of Infinite-Dimensional Statistical Models
• Measure theory. Vol. I and II
• Neural network approximation
• Neural Network Learning
• New analysis of manifold embeddings and signal recovery from compressive measurements
• Nonlinear approximation and (deep) ReLU networks
• Nonparametric regression on low-dimensional manifolds using deep ReLU networks: function approximation and statistical recovery
• Nonparametric regression using deep neural networks with ReLU activation function
• On the Theory of Dynamic Programming
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• Optimal approximation rate of ReLU networks in terms of width and depth
• Optimal approximation with sparsely connected deep neural networks
• Provable approximation properties for deep neural networks
• Representation formulas and pointwise properties for Barron functions
• Testing the manifold hypothesis
• The Modern Mathematics of Deep Learning
• Universal approximation bounds for superpositions of a sigmoidal function

Cited in

(5)

• Adaptive approximation and generalization of deep neural network with intrinsic dimensionality
• Nonparametric regression on low-dimensional manifolds using deep ReLU networks: function approximation and statistical recovery
• A deep network construction that adapts to intrinsic dimensionality beyond the domain
• Improving the expressive power of deep neural networks through integral activation transform
• Multivariate neural network operators: simultaneous approximation and Voronovskaja-type theorem

This page was built for publication: Low dimensional approximation and generalization of multivariate functions on smooth manifolds using deep ReLU neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6536393)