非线性随机矩阵的测度浓缩及其对神经网络与非交换多项式的应用
概率论
2025-07-15 v2 机器学习
摘要
我们证明了几类非线性随机矩阵的浓度不等式。作为推论，我们获得了共轭核函数（神经网络和非交换多项式）在（可能相关的）随机矩阵中的线性谱统计的估计。
引用
@article{arxiv.2507.07625,
title = {Concentration of measure for non-linear random matrices with applications to neural networks and non-commutative polynomials},
author = {Radosław Adamczak},
journal= {arXiv preprint arXiv:2507.07625},
year = {2025}
}
备注
Some typos fixed (and some new probably introduced), small editorial changes