[Submitted on 14 Oct 2026 (v1), last revised 12 Nov 2026 (this version, v2)]
Abstract: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 $1le m le n$, extending results of Hanin-Sellke and Hwang.
Submission history
From: Ben Weinkove [view email]
[v1] Wed, 14 Oct 2026 14:11:54 UTC (13 KB)
[v2] Thu, 12 Nov 2026 16:47:58 UTC (14 KB)
