On random matrices arising in deep neural networks: General I.I.D. case

DOI10.1142/s2010326322500460zbMath1517.60015arXiv2011.11439OpenAlexW3106743998WikidataQ114071582 ScholiaQ114071582MaRDI QIDQ6163573

Victor Slavin, Leonid Pastur

Publication date: 26 June 2023

Published in: Random Matrices: Theory and Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2011.11439

zbMATH Keywords

eigenvalue distributionrandom matricesdeep neural networks

Mathematics Subject Classification ID

Random matrices (probabilistic aspects) (60B20) Neural networks for/in biological studies, artificial life and related topics (92B20)

Related Items

Large-dimensional random matrix theory and its applications in deep learning and wireless communications, Linear eigenvalue statistics of XX′ matrices, The Law of Multiplication of Large Random Matrices Revisited

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Free probability and random matrices
• Spectral analysis of large dimensional random matrices
• Random matrices: universality of ESDs and the circular law
• Analysis of the limiting spectral measure of large random matrices of the separable covariance type
• The loss surfaces of neural networks with general activation functions
• Asymptotic spectra of matrix-valued functions of independent random matrices and free probability
• Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?
• High-Dimensional Probability
• Deep Neural Networks in a Mathematical Framework
• On the asymptotic eigenvalue distribution of concatenated vector-valued fading channels
• The Principles of Deep Learning Theory
• DISTRIBUTION OF EIGENVALUES FOR SOME SETS OF RANDOM MATRICES