Spectral Barron space for deep neural network approximation

Abstract

We prove the sharp embedding between the spectral Barron space and the Besov space with embedding constants independent of the input dimension. Given the spectral Barron space as the target function space, we prove a dimension-free convergence result that if the neural network contains $L$ hidden layers with $N$ units per layer, then the upper and lower bounds of the $L^2$-approximation error are $\mathcal{O}(N^{-sL})$ with $0<sL\le 1/2$, where $s\ge 0$ is the smoothness index of the spectral Barron space.

32 pages

References in corpus (6)

• Approximation and learning by greedy algorithms
• A Priori Estimates of the Population Risk for Two-layer Neural Networks
• The Finite Neuron Method and Convergence Analysis
• Sharp Bounds on the Approximation Rates, Metric Entropy, and $n$-widths of Shallow Neural Networks
• What Kinds of Functions do Deep Neural Networks Learn? Insights from Variational Spline Theory
• Near-Minimax Optimal Estimation With Shallow ReLU Neural Networks

Cited by in corpus (1)

• Generalization Error Estimates of Machine Learning Methods for Solving High Dimensional Schrödinger Eigenvalue Problems