2000 character limit reached
Optimal Approximation Complexity of High-Dimensional Functions with Neural Networks (2301.13091v1)
Published 30 Jan 2023 in cs.LG and cs.NE
Abstract: We investigate properties of neural networks that use both ReLU and $x2$ as activation functions and build upon previous results to show that both analytic functions and functions in Sobolev spaces can be approximated by such networks of constant depth to arbitrary accuracy, demonstrating optimal order approximation rates across all nonlinear approximators, including standard ReLU networks. We then show how to leverage low local dimensionality in some contexts to overcome the curse of dimensionality, obtaining approximation rates that are optimal for unknown lower-dimensional subspaces.