Full error analysis for the training of deep neural networks (Q5083408)

scientific article; zbMATH DE number 7544505

Language	Label	Description	Also known as
default for all languages	No label defined
English	Full error analysis for the training of deep neural networks	scientific article; zbMATH DE number 7544505

Statements

instance of

scholarly article

0 references

title

Full error analysis for the training of deep neural networks (English)

0 references

0 references

0 references

0 references

Infinite Dimensional Analysis, Quantum Probability and Related Topics

0 references

publication date

20 June 2022

0 references

full work available at URL

https://arxiv.org/abs/1910.00121

0 references

zbMATH Keywords

full error analysis

0 references

optimization error

0 references

generalization error

0 references

approximation error

0 references

machine learning

0 references

convergence analysis

0 references

artificial neural networks

0 references

MaRDI profile type

MaRDI publication profile

0 references

cites work

Breaking the curse of dimensionality with convex neural networks

0 references

Universal approximation bounds for superpositions of a sigmoidal function

0 references

Approximation and estimation bounds for artificial neural networks

0 references

Local Rademacher complexities

0 references

Solving the Kolmogorov PDE by means of deep learning

0 references

Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations

0 references

Q3574973

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

Error bounds for approximation with neural networks

0 references

On Stochastic Gradient Langevin Dynamics with Dependent Data Streams: The Fully Nonconvex Case

0 references

A proof of convergence for gradient descent in the training of artificial neural networks for constant target functions

0 references

Neural Networks for Localized Approximation

0 references

On the mathematical foundations of learning

0 references

Approximation by superpositions of a sigmoidal function

0 references

General multilevel adaptations for stochastic approximation algorithms of Robbins-Monro and Polyak-Ruppert type

0 references

Q4365433

0 references

A comparative analysis of optimization and generalization properties of two-layer neural network and random feature models under gradient descent dynamics

0 references

Exponential convergence of the deep neural network approximation for analytic functions

0 references

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

0 references

Q4310147

0 references

Convergence rates for the stochastic gradient descent method for non-convex objective functions

0 references

Deep learning

0 references

Approximation spaces of deep neural networks

0 references

Deep Neural Network Approximation Theory

0 references

Error bounds for approximations with deep ReLU neural networks in \(W^{s , p}\) norms

0 references

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

0 references

A distribution-free theory of nonparametric regression

0 references

Probability Inequalities for Sums of Bounded Random Variables

0 references

Multilayer feedforward networks are universal approximators

0 references

Deep neural networks algorithms for stochastic control problems on finite horizon: convergence analysis

0 references

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

0 references

Strong error analysis for stochastic gradient descent optimization algorithms

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

Lower error bounds for the stochastic gradient descent optimization algorithm: sharp convergence rates for slowly and fast decaying learning rates

0 references

A theoretical analysis of deep neural networks and parametric PDEs

0 references

Sets of finite perimeter and geometric variational problems. An introduction to geometric measure theory

0 references

Degree of approximation by neural and translation networks with a single hidden layer

0 references

Deep vs. shallow networks: an approximation theory perspective

0 references

Approximation of functions and their derivatives: A neural network implementation with applications

0 references

Tractability of multivariate problems. Volume I: Linear information

0 references

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

0 references

Topological properties of the set of functions generated by neural networks of fixed size

0 references

Optimal approximation of piecewise smooth functions using deep ReLU neural networks

0 references

Equivalence of approximation by convolutional neural networks and fully-connected networks

0 references

Q4938227

0 references

Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems

0 references

Deep learning in high dimension: neural network expression rates for generalized polynomial chaos expansions in UQ

0 references

Provable approximation properties for deep neural networks

0 references

Understanding machine learning. From theory to algorithms

0 references

Nonlinear approximation via compositions

0 references

Deep network approximation characterized by number of neurons

0 references

Q4944751

0 references

Error bounds for approximations with deep ReLU networks

0 references

Universal approximations of invariant maps by neural networks

0 references

Gradient descent optimizes over-parameterized deep ReLU networks

0 references

Identifiers

zbMATH Open document ID

1492.65132

0 references

DOI

10.1142/S021902572150020X

0 references

Mathematics Subject Classification ID

0 references

0 references

0 references

0 references

0 references

Sitelinks

Mathematics(1 entry)

mardi Publication:5083408