A note on the Pennington-Worah distribution

DOI10.1214/19-ECP262zbMath1423.60032MaRDI QIDQ2332995

Sandrine 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

random matricesmachine learning

Mathematics Subject Classification ID

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

Related Items (3)

Random neural networks in the infinite width limit as Gaussian processes ⋮ Eigenvalue distribution of some nonlinear models of random matrices ⋮ Triple descent and the two kinds of overfitting: where and why do they appear?*

Cites Work

• Unnamed Item
• The spectrum of kernel random matrices
• A random matrix approach to neural networks
• On a surprising relation between the Marchenko-Pastur law, rectangular and square free convolutions
• Eigenvalue distribution of some nonlinear models of random matrices
• Products of many large random matrices and gradients in deep neural networks
• On the empirical distribution of eigenvalues of large dimensional information-plus-noise-type matrices
• Limiting Eigenvectors of Outliers for Spiked Information-Plus-Noise Type Matrices
• Exact separation phenomenon for the eigenvalues of large Information-Plus-Noise type matrices. Application to spiked models
• Nonlinear random matrix theory for deep learning

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