Concentration of measure for non-linear random matrices with applications to neural networks and non-commutative polynomials
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 7 of its 52 references that are in the map. First posted on arXiv 10 Jul 2025.
Builds on
7 of 52 references.
References · 7
- 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
- 2020Loss landscapes and optimization in over-parameterized non-linear systems and neural networkscited by 233
- 2017Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practicecited by 132
- 2022Spectral Evolution and Invariance in Linear-width Neural Networkscited by 30
- 2022Eigenvalue Distribution of Large Random Matrices Arising in Deep Neural Networks: Orthogonal Casecited by 4
- 2020A Concentration of Measure and Random Matrix Approach to Large Dimensional Robust Statisticscited by 3
- 2025Global law of conjugate kernel random matrices with heavy-tailed weightscited by 3
Built on by
Not cited yet.