Quantitative convergence of trained single layer neural networks to Gaussian processes
训练单层神经网络向高斯过程定量收敛性
机构 * Department of Mathematics University of Pisa(数学系,比萨大学) ; Department of Mathematics and Statistics University of Bern(数学与统计系,伯恩大学)
AI总结 本文研究了训练单层神经网络在无限宽度极限下向高斯过程的定量收敛性,提供了网络输出与高斯近似之间距离的显式上界,并分析了架构参数和训练动态对收敛性的影响。
Comments Submitted and accepted at NeurIPS 2025, main body of 10 pages, 3 figures, 28 pages of supplementary material. Corrected an issue in the proof of Proposition 3.7