Lower bounds for artificial neural network approximations: a proof that shallow neural networks fail to overcome the curse of dimensionality (Q6155895): Difference between revisions

Latest revision as of 08:16, 1 August 2024

scientific article; zbMATH DE number 7693253

Language	Label	Description	Also known as
English	Lower bounds for artificial neural network approximations: a proof that shallow neural networks fail to overcome the curse of dimensionality	scientific article; zbMATH DE number 7693253

Statements

instance of

scholarly article

0 references

title

Lower bounds for artificial neural network approximations: a proof that shallow neural networks fail to overcome the curse of dimensionality (English)

0 references

arXiv ID

2103.04488

0 references

DOI

10.1016/j.jco.2023.101746

0 references

0 references

0 references

0 references

0 references

Journal of Complexity

0 references

publication date

7 June 2023

0 references

full work available at URL

https://arxiv.org/abs/2103.04488

0 references

Mathematics Subject Classification ID

0 references

0 references

0 references

0 references

artificial neural networks

0 references

artificial neural network approximations

0 references

curse of dimensionality

0 references

overcoming the curse of dimensionality

0 references

lower bounds

0 references

MaRDI profile type

MaRDI publication profile

0 references

0 references

0 references

Universal approximation bounds for superpositions of a sigmoidal function

0 references

Approximation and estimation bounds for artificial neural networks

0 references

An overview on deep learning-based approximation methods for partial differential equations

0 references

Full error analysis for the training of deep neural networks

0 references

Q5519768

0 references

Analysis of the Generalization Error: Empirical Risk Minimization over Deep Artificial Neural Networks Overcomes the Curse of Dimensionality in the Numerical Approximation of Black--Scholes Partial Differential Equations

0 references

Optimal Approximation with Sparsely Connected Deep Neural Networks

0 references

Approximation by superpositions of a sigmoidal function

0 references

Rates of convex approximation in non-Hilbert spaces

0 references

Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning

0 references

DNN expression rate analysis of high-dimensional PDEs: application to option pricing

0 references

Uniform error estimates for artificial neural network approximations for heat equations

0 references

Space-time error estimates for deep neural network approximations for differential equations

0 references

Deep neural network approximations for solutions of PDEs based on Monte Carlo algorithms

0 references

On the approximation by single hidden layer feedforward neural networks with fixed weights

0 references

Approximation and learning of convex superpositions

0 references

Multilayer feedforward networks are universal approximators

0 references

A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations

0 references

Proof that deep artificial neural networks overcome the curse of dimensionality in the numerical approximation of Kolmogorov partial differential equations with constant diffusion and nonlinear drift coefficients

0 references

A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training

0 references

Complexity of Gaussian-radial-basis networks approximating smooth functions

0 references

Dependence of Computational Models on Input Dimension: Tractability of Approximation and Optimization Tasks

0 references

Wahrscheinlichkeitstheorie

0 references

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

0 references

Minimization of Error Functionals over Perceptron Networks

0 references

Comparison of worst case errors in linear and neural network approximation

0 references

Geometric Upper Bounds on Rates of Variable-Basis Approximation

0 references

Lower bounds for approximation by MLP neural networks

0 references

Deep vs. shallow networks: An approximation theory perspective

0 references

Tractability of multivariate problems. Volume I: Linear information

0 references

Tractability of multivariate problems. Volume II: Standard information for functionals.

0 references

Optimal approximation of piecewise smooth functions using deep ReLU neural networks

0 references

Q4938227

0 references

A Remark on Stirling's Formula

0 references

Q4716292

0 references

Error bounds for approximations with deep ReLU networks

0 references

Sitelinks

Mathematics(1 entry)

mardi Publication:6155895

@@ Property / cites work @@
+Q4222737
@@ Property / cites work: Q4222737 / rank @@
+Normal rank
@@ Property / cites work @@
+Universal approximation bounds for superpositions of a sigmoidal function
+Normal rank
@@ Property / cites work @@
+Approximation and estimation bounds for artificial neural networks
+Normal rank
@@ Property / cites work @@
+An overview on deep learning-based approximation methods for partial differential equations
+Normal rank
@@ Property / cites work @@
+Full error analysis for the training of deep neural networks
+Normal rank
@@ Property / cites work @@
+Q5519768
@@ Property / cites work: Q5519768 / rank @@
+Normal rank
@@ Property / cites work @@
+Analysis of the Generalization Error: Empirical Risk Minimization over Deep Artificial Neural Networks Overcomes the Curse of Dimensionality in the Numerical Approximation of Black--Scholes Partial Differential Equations
+Normal rank
@@ Property / cites work @@
+Optimal Approximation with Sparsely Connected Deep Neural Networks
+Normal rank
@@ Property / cites work @@
+Approximation by superpositions of a sigmoidal function
+Normal rank
@@ Property / cites work @@
+Rates of convex approximation in non-Hilbert spaces
+Normal rank
@@ Property / cites work @@
+Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning
+Normal rank
@@ Property / cites work @@
+DNN expression rate analysis of high-dimensional PDEs: application to option pricing
+Normal rank
@@ Property / cites work @@
+Uniform error estimates for artificial neural network approximations for heat equations
+Normal rank
@@ Property / cites work @@
+Space-time error estimates for deep neural network approximations for differential equations
+Normal rank
@@ Property / cites work @@
+Deep neural network approximations for solutions of PDEs based on Monte Carlo algorithms
+Normal rank
@@ Property / cites work @@
+On the approximation by single hidden layer feedforward neural networks with fixed weights
+Normal rank
@@ Property / cites work @@
+Approximation and learning of convex superpositions
+Normal rank
@@ Property / cites work @@
+Multilayer feedforward networks are universal approximators
+Normal rank
@@ Property / cites work @@
+A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
+Normal rank
@@ Property / cites work @@
+Proof that deep artificial neural networks overcome the curse of dimensionality in the numerical approximation of Kolmogorov partial differential equations with constant diffusion and nonlinear drift coefficients
+Normal rank
@@ Property / cites work @@
+A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
+Normal rank
@@ Property / cites work @@
+Complexity of Gaussian-radial-basis networks approximating smooth functions
+Normal rank
@@ Property / cites work @@
+Dependence of Computational Models on Input Dimension: Tractability of Approximation and Optimization Tasks
+Normal rank
@@ Property / cites work @@
+Wahrscheinlichkeitstheorie
@@ Property / cites work: Wahrscheinlichkeitstheorie / rank @@
+Normal rank
@@ Property / cites work @@
+Approximation by Combinations of ReLU and Squared ReLU Ridge Functions With &lt;inline-formula&gt;                       &lt;tex-math notation="LaTeX"&gt;$\ell^1$ &lt;/tex-math&gt;                   &lt;/inline-formula&gt; and &lt;inline-formula&gt;                       &lt;tex-math notation="LaTeX"&gt;$\ell^0$ &lt;/tex-math&gt;                   &lt;/inline-formula&gt; Controls
+Normal rank
@@ Property / cites work @@
+Minimization of Error Functionals over Perceptron Networks
+Normal rank
@@ Property / cites work @@
+Comparison of worst case errors in linear and neural network approximation
+Normal rank
@@ Property / cites work @@
+Geometric Upper Bounds on Rates of Variable-Basis Approximation
+Normal rank
@@ Property / cites work @@
+Lower bounds for approximation by MLP neural networks
+Normal rank
@@ Property / cites work @@
+Deep vs. shallow networks: An approximation theory perspective
+Normal rank
@@ Property / cites work @@
+Tractability of multivariate problems. Volume I: Linear information
+Normal rank
@@ Property / cites work @@
+Tractability of multivariate problems. Volume II: Standard information for functionals.
+Normal rank
@@ Property / cites work @@
+Optimal approximation of piecewise smooth functions using deep ReLU neural networks
+Normal rank
@@ Property / cites work @@
+Q4938227
@@ Property / cites work: Q4938227 / rank @@
+Normal rank
@@ Property / cites work @@
+A Remark on Stirling's Formula
@@ Property / cites work: A Remark on Stirling's Formula / rank @@
+Normal rank
@@ Property / cites work @@
+Q4716292
@@ Property / cites work: Q4716292 / rank @@
+Normal rank
@@ Property / cites work @@
+Error bounds for approximations with deep ReLU networks
+Normal rank