New Error Bounds for Deep ReLU Networks Using Sparse Grids

Publication date: 3 February 2022

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1712.08688

zbMATH Keywords

neural networks sparse grids approximation theory curse of dimensionality machine learning deep networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Multidimensional problems (41A63)

Related Items (36)

Int-Deep: a deep learning initialized iterative method for nonlinear problems ⋮ Stationary Density Estimation of Itô Diffusions Using Deep Learning ⋮ SelectNet: self-paced learning for high-dimensional partial differential equations ⋮ ReLU deep neural networks from the hierarchical basis perspective ⋮ Convergence Rate Analysis for Deep Ritz Method ⋮ Deep ReLU Networks Overcome the Curse of Dimensionality for Generalized Bandlimited Functions ⋮ DeepParticle: learning invariant measure by a deep neural network minimizing Wasserstein distance on data generated from an interacting particle method ⋮ A note on the applications of one primary function in deep neural networks ⋮ Simultaneous neural network approximation for smooth functions ⋮ Deep Neural Networks for Solving Large Linear Systems Arising from High-Dimensional Problems ⋮ Neural network approximation: three hidden layers are enough ⋮ On the approximation of functions by tanh neural networks ⋮ Deep ReLU neural network approximation in Bochner spaces and applications to parametric PDEs ⋮ Rates of approximation by ReLU shallow neural networks ⋮ DEEP EQUILIBRIUM NETS ⋮ Three ways to solve partial differential equations with neural networks — A review ⋮ Deep ReLU neural networks in high-dimensional approximation ⋮ Solving nonconvex energy minimization problems in martensitic phase transitions with a mesh-free deep learning approach ⋮ Overall error analysis for the training of deep neural networks via stochastic gradient descent with random initialisation ⋮ SignReLU neural network and its approximation ability ⋮ Deep Neural Networks with ReLU-Sine-Exponential Activations Break Curse of Dimensionality in Approximation on Hölder Class ⋮ A Variational Neural Network Approach for Glacier Modelling with Nonlinear Rheology ⋮ Collocation approximation by deep neural ReLU networks for parametric and stochastic PDEs with lognormal inputs ⋮ Model reduction of coupled systems based on non-intrusive approximations of the boundary response maps ⋮ Deep ReLU networks and high-order finite element methods ⋮ Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems ⋮ A mesh-free method for interface problems using the deep learning approach ⋮ ExSpliNet: An interpretable and expressive spline-based neural network ⋮ Deep Network Approximation for Smooth Functions ⋮ Better Approximations of High Dimensional Smooth Functions by Deep Neural Networks with Rectified Power Units ⋮ Deep Network Approximation Characterized by Number of Neurons ⋮ Error bounds for deep ReLU networks using the Kolmogorov-Arnold superposition theorem ⋮ Deep Network With Approximation Error Being Reciprocal of Width to Power of Square Root of Depth ⋮ Approximation of functions from korobov spaces by deep convolutional neural networks ⋮ Error bounds for ReLU networks with depth and width parameters ⋮ Approximating functions with multi-features by deep convolutional neural networks

Cites Work

This page was built for publication: New Error Bounds for Deep ReLU Networks Using Sparse Grids