Score: 0

Integral Representations of Sobolev Spaces via ReLU$^k$ Activation Function and Optimal Error Estimates for Linearized Networks

Published: May 1, 2025 | arXiv ID: 2505.00351v2

By: Xinliang Liu, Tong Mao, Jinchao Xu

Potential Business Impact:

Makes computers learn math faster and better.

Business Areas:
Alumni Education

This paper presents two main theoretical results concerning shallow neural networks with ReLU$^k$ activation functions. We establish a novel integral representation for Sobolev spaces, showing that every function in $H^{\frac{d+2k+1}{2}}(\Omega)$ can be expressed as an $L^2$-weighted integral of ReLU$^k$ ridge functions over the unit sphere. This result mirrors the known representation of Barron spaces and highlights a fundamental connection between Sobolev regularity and neural network representations. Moreover, we prove that linearized shallow networks -- constructed by fixed inner parameters and optimizing only the linear coefficients -- achieve optimal approximation rates $O(n^{-\frac{1}{2}-\frac{2k+1}{2d}})$ in Sobolev spaces.

Page Count
41 pages

Category
Mathematics:
Numerical Analysis (Math)