No confident code implementation found for this paper.
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.
No confident code match yet
We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.
No code implementations found yet.
Know of an implementation? Let us know in the comments below!
Genus expansion for non-linear random matrix ensembles with applications to neural networks
A Theory of Diversity for Random Matrices with Applications to In-Context Learning of Schrödinger Equations
Nonlinear Random Matrices and Applications to the Sum of Squares Hierarchy
Random matrix theory and the loss surfaces of neural networks
Entropic bounds for conditionally Gaussian vectors and applications to neural networks
Neural Tangent Kernels and Fisher Information Matrices for Simple ReLU Networks with Random Hidden Weights
@article{adamczak2025concentration,
title = {Concentration of measure for non-linear random matrices with applications to neural networks and non-commutative polynomials},
author = {Radosław Adamczak},
year = {2025},
eprint = {2507.07625},
archivePrefix = {arXiv},
url = {http://arxiv.org/abs/2507.07625v2}
}Shows whether official code is linked for this paper.
[](https://codeofpaper.com/paper/2507.07625)