A note on the Pennington-Worah distribution

DOI10.1214/19-ECP262zbMATH Open1423.60032MaRDI QIDQ2332995FDOQ2332995

S. Péché

Publication date: 6 November 2019

Published in: Electronic Communications in Probability (Search for Journal in Brave)

Full work available at URL: https://projecteuclid.org/euclid.ecp/1572509100

zbMATH Keywords

machine learningrandom matrices

Mathematics Subject Classification ID

Probability distributions: general theory (60E05) Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Title not available (Why is that?)
• On the empirical distribution of eigenvalues of large dimensional information-plus-noise-type matrices
• The spectrum of kernel random matrices
• On a surprising relation between the Marchenko-Pastur law, rectangular and square free convolutions
• A random matrix approach to neural networks
• Exact separation phenomenon for the eigenvalues of large Information-Plus-Noise type matrices. Application to spiked models
• Products of many large random matrices and gradients in deep neural networks
• Limiting Eigenvectors of Outliers for Spiked Information-Plus-Noise Type Matrices
• Nonlinear random matrix theory for deep learning
• Eigenvalue distribution of some nonlinear models of random matrices

Cited In (5)

• Random neural networks in the infinite width limit as Gaussian processes
• Deformed semicircle law and concentration of nonlinear random matrices for ultra-wide neural networks
• Triple descent and the two kinds of overfitting: where and why do they appear?*
• A Note on Wadley's Problem with Overdispersion
• Eigenvalue distribution of some nonlinear models of random matrices

This page was built for publication: A note on the Pennington-Worah distribution

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2332995)