[Submitted on 28 Sep 2026 (v1), last revised 19 Nov 2026 (this version, v2)]
Abstract:We study the minimum number of hidden neurons required for arbitrary-accuracy approximation of continuous functions on $[0,1]^d$ and the associated encoding complexity. For $dgeq 2$, we construct two fixed, explicitly defined activation functions and, for each, a closed-form network with two hidden layers of widths $d$ and $1$ that achieves arbitrary accuracy in the uniform norm. We prove that $d+1$ is the exact minimum total number of hidden neurons among standard feedforward networks with locally integrable activations and affine outputs. We further give a simpler construction using a single elementary activation that combines the floor and exponential functions. This construction requires three hidden layers of widths $d$, $1$, and $2$. If a skip connection is allowed, widths $d$, $1$, and $1$ suffice. For a bounded $alpha$-Hölder class with $alphain(0,1]$, the networks with the digit-extraction activation and with the elementary activation require $O(varepsilon^{-d/alpha}log(1/varepsilon))$ bits, matching the metric-entropy lower bound up to a logarithmic factor. The other $(d,1)$ network, which stores differences of neighboring values along a spanning tree, needs only $Theta(varepsilon^{-d/alpha})$ bits and is optimal in both neuron count and bit complexity.
Submission history
From: Zilan Cheng [view email]
[v1] Mon, 28 Sep 2026 17:00:04 UTC (1,647 KB)
[v2] Thu, 19 Nov 2026 10:41:21 UTC (1,690 KB)
