40 citations · 40 across the 1 of their papers we have counts for
3 papers
cs.LG2019★ 40 cited
Traditional and Heavy-Tailed Self Regularization in Neural Network Models
Charles H. Martin, Michael W. Mahoney
Random Matrix Theory (RMT) is applied to analyze the weight matrices of Deep Neural Networks (DNNs), including both production quality, pre-trained models such as AlexNet and Incep…
cs.LG2019
Heavy-Tailed Universality Predicts Trends in Test Accuracies for Very Large Pre-Trained Deep Neural Networks
Charles H. Martin, Michael W. Mahoney
Given two or more Deep Neural Networks (DNNs) with the same or similar architectures, and trained on the same dataset, but trained with different solvers, parameters, hyper-paramet…
cs.LG2018
Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning
Charles H. Martin, Michael W. Mahoney
Random Matrix Theory (RMT) is applied to analyze weight matrices of Deep Neural Networks (DNNs), including both production quality, pre-trained models such as AlexNet and Inception…