Predicting trends in the quality of state-of-the-art neural networks
without access to training or testing data

Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data

17 February 2020

Charles H. Martin

Michael W. Mahoney

Papers citing "Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data"

14 / 64 papers shown

Title
Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data Yaoqing Yang Ryan Theisen Liam Hodgkinson Joseph E. Gonzalez Kannan Ramchandran Charles H. Martin Michael W. Mahoney 86 17 0 06 Feb 2022
Separation of Scales and a Thermodynamic Description of Feature Learning in Some CNNs Inbar Seroussi Gadi Naveh Z. Ringel 30 50 0 31 Dec 2021
Learning from learning machines: a new generation of AI technology to meet the needs of science L. Pion-Tonachini K. Bouchard Héctor García Martín S. Peisert W. B. Holtz ... Rick L. Stevens Mark Anderson Ken Kreutz-Delgado Michael W. Mahoney James B. Brown 30 7 0 27 Nov 2021
Impact of classification difficulty on the weight matrices spectra in Deep Learning and application to early-stopping Xuran Meng Jianfeng Yao 22 7 0 26 Nov 2021
An Operator Theoretic View on Pruning Deep Neural Networks William T. Redman M. Fonoberova Ryan Mohr Y. Kevrekidis Igor Mezić 38 17 0 28 Oct 2021
Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers Liam Hodgkinson Umut Simsekli Rajiv Khanna Michael W. Mahoney 22 20 0 02 Aug 2021
Taxonomizing local versus global structure in neural network loss landscapes Yaoqing Yang Liam Hodgkinson Ryan Theisen Joe Zou Joseph E. Gonzalez Kannan Ramchandran Michael W. Mahoney 32 36 0 23 Jul 2021
Post-mortem on a deep learning contest: a Simpson's paradox and the complementary roles of scale metrics versus shape metrics Charles H. Martin Michael W. Mahoney 18 19 0 01 Jun 2021
Hessian Eigenspectra of More Realistic Nonlinear Models Zhenyu Liao Michael W. Mahoney 17 29 0 02 Mar 2021
Perceptron Theory Can Predict the Accuracy of Neural Networks Denis Kleyko A. Rosato E. P. Frady Massimo Panella Friedrich T. Sommer GNN 28 10 0 14 Dec 2020
Sparse Quantized Spectral Clustering Zhenyu Liao Romain Couillet Michael W. Mahoney MQ 19 15 0 03 Oct 2020
Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning Charles H. Martin Michael W. Mahoney AI4CE 32 190 0 02 Oct 2018
Cleaning large correlation matrices: tools from random matrix theory J. Bun J. Bouchaud M. Potters 32 262 0 25 Oct 2016
Norm-Based Capacity Control in Neural Networks Behnam Neyshabur Ryota Tomioka Nathan Srebro 119 577 0 27 Feb 2015