首页|Concentration of measure for non-linear random matrices with applications to neural networks and non-commutative polynomials

Concentration of measure for non-linear random matrices with applications to neural networks and non-commutative polynomials

来源：

Arxiv

英文摘要

We prove concentration inequalities for several models of non-linear random matrices. As corollaries we obtain estimates for linear spectral statistics of the conjugate kernel of neural networks and non-commutative polynomials in (possibly dependent) random matrices.

作者：Radosław Adamczak

作者单位：

学科分类：数学

推荐引用：Radosław Adamczak.Concentration of measure for non-linear random matrices with applications to neural networks and non-commutative polynomials[EB/OL].(2025-07-14)[2025-07-20].https://arxiv.org/abs/2507.07625.点此复制

Concentration of measure for non-linear random matrices with applications to neural networks and non-commutative polynomials

Concentration of measure for non-linear random matrices with applications to neural networks and non-commutative polynomials

评论