Sharp Bounds on the Approximation Rates, Metric Entropy, and n-Widths of Shallow Neural Networks

DOI10.1007/S10208-022-09595-3MaRDI QIDQ6489780FDOQ6489780

Publication date: 22 April 2024

Published in: Foundations of Computational Mathematics (Search for Journal in Brave)

Neural nets and related approaches to inference from stochastic processes (62M45) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46)

Cites Work

A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
Universal approximation bounds for superpositions of a sigmoidal function
Comparison of worst case errors in linear and neural network approximation
Convex Analysis
Random approximants and neural networks
Approximation and learning by greedy algorithms
Compressed sensing
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Eigenvalues, embeddings and generalised trigonometric functions
Title not available (Why is that?)
History of Banach Spaces and Linear Operators
Geometric discrepancy. An illustrated guide
Gelfand numbers of operators with values in a Hilbert space
The best constants in the Khintchine inequality
Title not available (Why is that?)
Title not available (Why is that?)
Uniform approximation by neural networks
Approximation rates for neural networks with general activation functions
s-Numbers of operators in Banach spaces
Entropy numbers, s-numbers, and eigenvalue problems
Information-theoretic determination of minimax rates of convergence
Optimal nonlinear approximation
The sizes of compact subsets of Hilbert space and continuity of Gaussian processes
Title not available (Why is that?)
Efficient agnostic learning of neural networks with bounded fan-in
On Lattices Admitting Unique Lagrange Interpolations
General Lagrange and Hermite interpolation in $R^n$ with applications to finite element methods
Estimation of Linear Functionals on Sobolev Spaces with Application to Fourier Transforms and Spline Interpolation
Inequalities of Bernstein-Jackson-type and the degree of compactness of operators in Banach spaces
Universal Donsker classes and metric entropy
Gelfand numbers and metric entropy of convex hulls in Hilbert spaces
Title not available (Why is that?)
Metric Entropy of Convex Hulls in Hilbert Spaces
Metric Entropy of Convex Hulls in Banach Spaces
Gelfand numbers and widths
Bounds on rates of variable-basis and neural-network approximation
Tight upper bounds for the discrepancy of half-spaces
On a Class of Finite Elements Generated by Lagrange Interpolation
Title not available (Why is that?)
Improved upper bounds for approximation by zonotopes
Entropy numbers of convex hulls in Banach spaces and applications
Breaking the Curse of Dimensionality with Convex Neural Networks
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
Finite Neuron Method and Convergence Analysis
High-order approximation rates for shallow neural networks with cosine and $\mathrm{ReLU}^k$ activation functions

Cited In (6)

A reduced conjugate gradient basis method for fractional diffusion
Two-layer networks with the $\text{ReLU}^k$ activation function: Barron spaces and derivative approximation
On the optimality of target-data-dependent kernel greedy interpolation in Sobolev reproducing kernel Hilbert spaces
Inequalities between s-numbers
An iterative method for the solution of Laplace-like equations in high and very high space dimensions
Entropy-based convergence rates of greedy algorithms

This page was built for publication: Sharp Bounds on the Approximation Rates, Metric Entropy, and n-Widths of Shallow Neural Networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6489780)