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

DOI10.1214/22-aap1884arXiv2011.09363MaRDI QIDQ6165247

Philipp Petersen, Felix Voigtlaender, Andrei Caragea

Publication date: 31 July 2023

Published in: The Annals of Applied Probability (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2011.09363

zbMATH Keywords

classificationapproximationempirical risk minimizationdeep neural networksReLU neural networksBarron spaces

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Function spaces arising in harmonic analysis (42B35) Rate of convergence, degree of approximation (41A25) Banach spaces of continuous, differentiable or analytic functions (46E15) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46)

Related Items

Deep Neural Networks for Solving Large Linear Systems Arising from High-Dimensional Problems, A priori generalization error analysis of two-layer neural networks for solving high dimensional Schrödinger eigenvalue problems, Learning ability of interpolating deep convolutional neural networks

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Linear functional analysis. An application-oriented introduction. Translated from the 6th German edition by Robert Nürnberg
• Uniform approximation by neural networks
• Approximation and estimation bounds for artificial neural networks
• Information-theoretic determination of minimax rates of convergence
• Provable approximation properties for deep neural networks
• Approximation rates for neural networks with general activation functions
• Efficient approximation of solutions of parametric linear transport equations by ReLU DNNs
• 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
• Representation formulas and pointwise properties for Barron functions
• DNN expression rate analysis of high-dimensional PDEs: application to option pricing
• Uniform approximation rates and metric entropy of shallow neural networks
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• Approximation of infinitely differentiable multivariate functions is intractable
• A priori estimates of the population risk for two-layer neural networks
• Universal approximation bounds for superpositions of a sigmoidal function
• Deep learning in high dimension: Neural network expression rates for generalized polynomial chaos expansions in UQ
• High-Dimensional Probability
• Neural Network Learning
• Solving high-dimensional partial differential equations using deep learning
• Deep Neural Network Approximation Theory
• Solving high-dimensional optimal stopping problems using deep learning
• Optimal Approximation with Sparsely Connected Deep Neural Networks
• 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
• Deep ReLU Networks Overcome the Curse of Dimensionality for Generalized Bandlimited Functions
• Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems
• Overcoming the curse of dimensionality in the numerical approximation of semilinear parabolic partial differential equations
• Understanding Machine Learning
• On the Theory of Dynamic Programming
• A deep network construction that adapts to intrinsic dimensionality beyond the domain