Uniform approximation rates and metric entropy of shallow neural networks

DOI10.1007/s40687-022-00346-yOpenAlexW4286218552WikidataQ114218935 ScholiaQ114218935MaRDI QIDQ2157931

Jonathan W. Siegel, Limin Ma, Jin-Chao Xu

Publication date: 22 July 2022

Published in: Research in the Mathematical Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s40687-022-00346-y

zbMATH Keywords

neural networksfinite element methodsmetric entropyapproximation rates

Mathematics Subject Classification ID

Biology and other natural sciences (92-XX) Approximations and expansions (41-XX)

Related Items (1)

Neural network approximation and estimation of classifiers with classification boundary in a Barron class

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Greedy function approximation: A gradient boosting machine.
• On the rate of convergence of greedy algorithms.
• The essential order of approximation for neural networks
• Entropy numbers, s-numbers, and eigenvalue problems
• A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
• Uniform approximation by neural networks
• Improved upper bounds for approximation by zonotopes
• The Deep Ritz Method: a deep learning-based numerical algorithm for solving variational problems
• Approximation of functions of finite variation by superpositions of a sigmoidal function.
• Some problems in the theory of ridge functions
• Tight upper bounds for the discrepancy of half-spaces
• Random approximants and neural networks
• Some remarks on greedy algorithms
• Representation formulas and pointwise properties for Barron functions
• High-order approximation rates for shallow neural networks with cosine and \(\mathrm{ReLU}^k\) activation functions
• Approximation and learning by greedy algorithms
• A combinatorial problem; stability and order for models and theories in infinitary languages
• On the density of families of sets
• Optimal stable nonlinear approximation
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Greedy Approximation
• Lower bounds for the rate of convergence of greedy algorithms
• Greedy approximation
• Approximation by Ridge Functions and Neural Networks
• Universal approximation bounds for superpositions of a sigmoidal function
• Metric Entropy of Convex Hulls in Hilbert Spaces
• Metric Entropy of Convex Hulls in Banach Spaces
• Bounds on rates of variable-basis and neural-network approximation
• Comparison of worst case errors in linear and neural network approximation
• 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
• Sup-norm approximation bounds for networks through probabilistic methods
• Matching pursuits with time-frequency dictionaries
• What Kinds of Functions Do Deep Neural Networks Learn? Insights from Variational Spline Theory
• Optimal Convergence Rates for the Orthogonal Greedy Algorithm
• Deep Network Approximation for Smooth Functions
• Finite Neuron Method and Convergence Analysis
• Breaking the Curse of Dimensionality with Convex Neural Networks
• Constructive Approximation by Superposition of Sigmoidal Functions
• Geometric discrepancy. An illustrated guide
• Approximation by superpositions of a sigmoidal function

This page was built for publication: Uniform approximation rates and metric entropy of shallow neural networks