arXiv:2610.20229 · v2

The minimal width of neural networks and immersions of real projective space

首次提交 2026-10-14 22:11

版本更新 2026-11-13 00:47

雷达观测 2026-11-13 14:15

摘要

We investigate the minimal width of deep neural networks that can approximate all continuous functions from $\mathbb{R}^n$ to $\mathbb{R}^m$ in the topology of uniform convergence on compact subsets. We show that whenever the real projective space $\mathbb{RP}^{n-1}$ admits a smooth immersion into $\mathbb{R}^n$, the minimal width is at least $n+\min\{n,m\}$, assuming that the activation function is continuous and monotone. As a consequence, the minimal width of ReLU networks is $n+m$ whenever $n$ is equal to 2, 3, 4, 7 or 8 and $1\le m \le n$, extending results of Hanin-Sellke and Hwang.

作者备注：12 pages; v2 reference added, minor corrections