Two-Layer Neural Networks with Values in a Banach Space

DOI10.1137/21M1458144MaRDI QIDQ5055293FDOQ5055293

Authors: Yury Korolev 

Publication date: 13 December 2022

Published in: SIAM Journal on Mathematical Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2105.02095

Recommendations

• Two-layer networks with the \(\text{ReLU}^k\) activation function: Barron spaces and derivative approximation
• Approximation spaces of deep neural networks
• Understanding neural networks with reproducing kernel Banach spaces
• Representation formulas and pointwise properties for Barron functions
• Multiple general sigmoids based Banach space valued neural network multivariate approximation

zbMATH Keywords

curse of dimensionalityBregman distanceReLUbarron spacevariation norm spacevector-valued neural networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Computational learning theory (68Q32) Abstract approximation theory (approximation in normed linear spaces and other abstract spaces) (41A65) Spaces of vector- and operator-valued functions (46E40) Numerical solution to inverse problems in abstract spaces (65J22)

Cites Work

• Universal approximation bounds for superpositions of a sigmoidal function
• Comparison of worst case errors in linear and neural network approximation
• On Learning Vector-Valued Functions
• Kernels for vector-valued functions: a review
• Title not available (Why is that?)
• A distribution-free theory of nonparametric regression
• Approximation and learning by greedy algorithms
• Title not available (Why is that?)
• Convergence rates of convex variational regularization
• Variational methods in imaging
• Banach lattices
• Title not available (Why is that?)
• Title not available (Why is that?)
• Multilayer feedforward networks are universal approximators
• Approximation by superpositions of a sigmoidal function
• Exact support recovery for sparse spikes deconvolution
• A counterexample to the approximation problem in Banach spaces
• Learning from examples as an inverse problem
• Convex regularization in statistical inverse learning problems
• Some applications of Rademacher sequences in Banach lattices
• Relative weak compactness of solid hulls in Banach lattices
• Model reduction and neural networks for parametric PDEs
• Bounds on rates of variable-basis and neural-network approximation
• Training neural networks with noisy data as an ill-posed problem
• Optimal rates for regularization of statistical inverse learning problems
• Inverse problems in spaces of measures
• On representer theorems and convex regularization
• Sparsity of solutions for variational inverse problems with finite-dimensional data
• Lipschitz algebras
• Variational regularisation for inverse problems with imperfect forward operators and general noise models
• Solving inverse problems using data-driven models
• A mean field view of the landscape of two-layer neural networks
• Breaking the curse of dimensionality with convex neural networks
• Neural network approximation
• Vector-valued reproducing kernel Banach spaces with applications to multi-task learning
• Bias reduction in variational regularization
• On debiasing restoration algorithms: applications to total-variation and nonlocal-means
• Modern regularization methods for inverse problems
• The implicit bias of gradient descent on separable data
• Mean field analysis of neural networks: a law of large numbers
• On the regularizing property of stochastic gradient descent
• Error estimates for DeepONets: a deep learning framework in infinite dimensions
• A theoretical analysis of deep neural networks and parametric PDEs
• Banach space representer theorems for neural networks and ridge splines
• A unifying representer theorem for inverse problems and machine learning
• The Random Feature Model for Input-Output Maps between Banach Spaces
• Trainability and Accuracy of Artificial Neural Networks: An Interacting Particle System Approach
• Representation formulas and pointwise properties for Barron functions
• The Barron space and the flow-induced function spaces for neural network models

Cited In (9)

• Operator learning using random features: a tool for scientific computing
• A Riemannian mean field formulation for two-layer neural networks with batch normalization
• Two-layer networks with the \(\text{ReLU}^k\) activation function: Barron spaces and derivative approximation
• Weighted variation spaces and approximation by shallow ReLU networks
• Neural-network-based regularization methods for inverse problems in imaging
• From kernel methods to neural networks: a unifying variational formulation
• Convergence Rates for Learning Linear Operators from Noisy Data
• Richards's curve induced Banach space valued multivariate neural network approximation
• Linearized two-layers neural networks in high dimension

Uses Software

• DeepONet

This page was built for publication: Two-Layer Neural Networks with Values in a Banach Space

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5055293)