跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2609.35628 · v2

Arbitrary-Accuracy Neural Approximation with Optimal Neuron Count and Optimal Bit Complexity

首次提交 2026-09-29 01:00
版本更新 2026-11-19 18:41
雷达观测 2026-11-20 19:57
arXiv ↗PDF ↗

摘要

We study the minimum number of hidden neurons required for arbitrary-accuracy approximation of continuous functions on [0,1]d[0,1]^d and the associated encoding complexity. For d≥2d\geq 2, we construct two fixed, explicitly defined activation functions and, for each, a closed-form network with two hidden layers of widths dd and 11 that achieves arbitrary accuracy in the uniform norm. We prove that d+1d+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 dd, 11, and 22. If a skip connection is allowed, widths dd, 11, and 11 suffice. For a bounded αα-Hölder class with α∈(0,1]α\in(0,1], the networks with the digit-extraction activation and with the elementary activation require O(ε−d/αlog⁡(1/ε))O(\varepsilon^{-d/α}\log(1/\varepsilon)) bits, matching the metric-entropy lower bound up to a logarithmic factor. The other (d,1)(d,1) network, which stores differences of neighboring values along a spanning tree, needs only Θ(ε−d/α)Θ(\varepsilon^{-d/α}) bits and is optimal in both neuron count and bit complexity.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v2,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-19 18:41 · 最新观测版本

Arbitrary-Accuracy Neural Approximation with Optimal Neuron Count and Optimal Bit Complexity

We study the minimum number of hidden neurons required for arbitrary-accuracy approximation of continuous functions on [0,1]d[0,1]^d and the associated encoding complexity. For d≥2d\geq 2, we construct two fixed, explicitly defined activation functions and, for each, a closed-form network with two hidden layers of widths dd and 11 that achieves arbitrary accuracy in the uniform norm. We prove that d+1d+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 dd, 11, and 22. If a skip connection is allowed, widths dd, 11, and 11 suffice. For a bounded αα-Hölder class with α∈(0,1]α\in(0,1], the networks with the digit-extraction activation and with the elementary activation require O(ε−d/αlog⁡(1/ε))O(\varepsilon^{-d/α}\log(1/\varepsilon)) bits, matching the metric-entropy lower bound up to a logarithmic factor. The other (d,1)(d,1) network, which stores differences of neighboring values along a spanning tree, needs only Θ(ε−d/α)Θ(\varepsilon^{-d/α}) bits and is optimal in both neuron count and bit complexity.

查看此版本解读 →查看此版本原文 ↗