Sharp uniform approximation for spectral Barron functions by deep neural networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912473035046912 |
|---|---|
| author | Liao, Yulei Ming, Pingbing Yu, Hao |
| author_facet | Liao, Yulei Ming, Pingbing Yu, Hao |
| contents | This work explores the neural network approximation capabilities for functions within the spectral Barron space $\mathscr{B}^s$, where $s$ is the smoothness index. We demonstrate that for functions in $\mathscr{B}^{1/2}$, a shallow neural network (a single hidden layer) with $N$ units can achieve an $L^p$-approximation rate of $\mathcal{O}(N^{-1/2})$. This rate also applies to uniform approximation, differing by at most a logarithmic factor. Our results significantly reduce the smoothness requirement compared to existing theory, which necessitate functions to belong to $\mathscr{B}^1$ in order to attain the same rate. Furthermore, we show that increasing the network's depth can notably improve the approximation order for functions with small smoothness. Specifically, for networks with $L$ hidden layers, functions in $\mathscr{B}^s$ with $0 < sL \le 1/2$ can achieve an approximation rate of $\mathcal{O}(N^{-sL})$. The rates and prefactors in our estimates are dimension-free. We also confirm the sharpness of our findings, with the lower bound closely aligning with the upper, with a discrepancy of at most one logarithmic factor. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_06789 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Sharp uniform approximation for spectral Barron functions by deep neural networks Liao, Yulei Ming, Pingbing Yu, Hao Numerical Analysis This work explores the neural network approximation capabilities for functions within the spectral Barron space $\mathscr{B}^s$, where $s$ is the smoothness index. We demonstrate that for functions in $\mathscr{B}^{1/2}$, a shallow neural network (a single hidden layer) with $N$ units can achieve an $L^p$-approximation rate of $\mathcal{O}(N^{-1/2})$. This rate also applies to uniform approximation, differing by at most a logarithmic factor. Our results significantly reduce the smoothness requirement compared to existing theory, which necessitate functions to belong to $\mathscr{B}^1$ in order to attain the same rate. Furthermore, we show that increasing the network's depth can notably improve the approximation order for functions with small smoothness. Specifically, for networks with $L$ hidden layers, functions in $\mathscr{B}^s$ with $0 < sL \le 1/2$ can achieve an approximation rate of $\mathcal{O}(N^{-sL})$. The rates and prefactors in our estimates are dimension-free. We also confirm the sharpness of our findings, with the lower bound closely aligning with the upper, with a discrepancy of at most one logarithmic factor. |
| title | Sharp uniform approximation for spectral Barron functions by deep neural networks |
| topic | Numerical Analysis |
| url | https://arxiv.org/abs/2507.06789 |