研究人员开发了一种方法，用于近似有限宽度神经网络与其无限宽度高斯极限之间的偏差。该方法使用多维Edgeworth展开来量化贝叶斯后验分布在进行近似时的误差。研究结果为真实网络输出与其近似值之间的总变差距离设定了上限，并给出了匹配的下限。 AI
影响 为理解和界定神经网络输出误差提供了理论框架，可能提高模型在统计应用中的准确性。
排序理由 该集群包含一篇学术论文，详细介绍了一种分析神经网络输出的新数学方法。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.24072v1 Announce Type: cross Abstract: Finite-width fully connected neural networks with Gaussian-initialized weights deviate from their infinite-width Gaussian limit, exhibiting non-vanishing higher-order cumulants. We approximate these deviations, for a neural networ…
Finite-width fully connected neural networks with Gaussian-initialized weights deviate from their infinite-width Gaussian limit, exhibiting non-vanishing higher-order cumulants. We approximate these deviations, for a neural network evaluated in a finite number of inputs, using mu…