A Surprising Linear Relationship Predicts Test Performance in Deep Networks

25 July 2018

Papers citing "A Surprising Linear Relationship Predicts Test Performance in Deep Networks"

6 / 6 papers shown

Title
Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data Charles H. Martin Tongsu Peng Peng Michael W. Mahoney 36 101 0 17 Feb 2020
Theoretical Issues in Deep Networks: Approximation, Optimization and Generalization T. Poggio Andrzej Banburski Q. Liao ODL 31 161 0 25 Aug 2019
An Effective Label Noise Model for DNN Text Classification Ishan Jindal Daniel Pressel Brian Lester M. Nokleby NoLa 32 48 0 18 Mar 2019
An Empirical Study of Large-Batch Stochastic Gradient Descent with Structured Covariance Noise Yeming Wen Kevin Luk Maxime Gazeau Guodong Zhang Harris Chan Jimmy Ba ODL 20 22 0 21 Feb 2019
Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning Charles H. Martin Michael W. Mahoney AI4CE 44 191 0 02 Oct 2018
Rethinking generalization requires revisiting old ideas: statistical mechanics approaches and complex learning behavior Charles H. Martin Michael W. Mahoney AI4CE 30 62 0 26 Oct 2017