Deep Learning in High Dimension: Neural Network Expression Rates for Analytic Functions in \(\pmb{L^2(\mathbb{R}^d,\gamma_d)}\)

DOI10.1137/21m1462738zbMath1524.41084arXiv2111.07080OpenAlexW4323048626MaRDI QIDQ6109160

J. Zech, Christoph Schwab

Publication date: 30 June 2023

Published in: SIAM/ASA Journal on Uncertainty Quantification (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2111.07080

zbMATH Keywords

neural networksanalytic functionsGaussian measuresexpression rates

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Orthogonal polynomials and functions of hypergeometric type (Jacobi, Laguerre, Hermite, Askey scheme, etc.) (33C45) Multidimensional problems (41A63) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46)

Cites Work

• Parabolic molecules
• Isotropic Gaussian random fields on the sphere: regularity, fast simulation and stochastic partial differential equations
• Expansions for Gaussian processes and Parseval frames
• Approximation spaces of deep neural networks
• Exponential ReLU DNN expression of holomorphic maps in high dimension
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• Error bounds for approximations with deep ReLU networks
• The orthogonal development of non-linear functionals in series of Fourier-Hermite functionals
• Sparse polynomial approximation of parametric elliptic PDEs. Part II: lognormal coefficients
• An Inequality for Hermite Polynomials
• Gaussian Hilbert Spaces
• Electromagnetic wave scattering by random surfaces: Shape holomorphy
• Posterior consistency for Gaussian process approximations of Bayesian posterior distributions
• Deep learning in high dimension: Neural network expression rates for generalized polynomial chaos expansions in UQ
• Deep Neural Network Approximation Theory
• Convergence rates of high dimensional Smolyak quadrature
• PowerNet: Efficient Representations of Polynomials and Smooth Functions by Deep Neural Networks with Rectified Power Units
• Deep ReLU networks and high-order finite element methods
• N-TERM WIENER CHAOS APPROXIMATION RATES FOR ELLIPTIC PDEs WITH LOGNORMAL GAUSSIAN RANDOM INPUTS
• The Homogeneous Chaos
• Contributions to the Theory of Hermitian Series II. The Representation Problem
• A Stochastic Collocation Method for Elliptic Partial Differential Equations with Random Input Data
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Deep Learning in High Dimension: Neural Network Expression Rates for Analytic Functions in \(\pmb{L^2(\mathbb{R}^d,\gamma_d)}\)