Charles H. Martin

Publication Activity (10 Years)

Years Active: 2017-2023
Publications (10 Years): 14

Top Topics

Statistical Mechanics

Discovering Knowledge

Top Venues

J. Mach. Learn. Res.

Publications

Yefan Zhou, Tianyu Pang, Keqin Liu, Charles H. Martin, Michael W. Mahoney, Yaoqing Yang
Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training. NeurIPS (2023)
Yaoqing Yang, Ryan Theisen, Liam Hodgkinson, Joseph E. Gonzalez, Kannan Ramchandran, Charles H. Martin, Michael W. Mahoney
Test Accuracy vs. Generalization Gap: Model Selection in NLP without Accessing Training or Testing Data. KDD (2023)
Yefan Zhou, Tianyu Pang, Keqin Liu, Charles H. Martin, Michael W. Mahoney, Yaoqing Yang
Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training. CoRR (2023)
Yaoqing Yang, Ryan Theisen, Liam Hodgkinson, Joseph E. Gonzalez, Kannan Ramchandran, Charles H. Martin, Michael W. Mahoney
Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data. CoRR (2022)
Charles H. Martin, Michael W. Mahoney
Post-mortem on a deep learning contest: a Simpson's paradox and the complementary roles of scale metrics versus shape metrics. CoRR (2021)
Charles H. Martin, Michael W. Mahoney
Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning. J. Mach. Learn. Res. 22 (2021)
Charles H. Martin, Michael W. Mahoney
Heavy-Tailed Universality Predicts Trends in Test Accuracies for Very Large Pre-Trained Deep Neural Networks. SDM (2020)
Charles H. Martin, Tongsu Peng, Michael W. Mahoney
Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data. CoRR (2020)
Charles H. Martin, Michael W. Mahoney
Traditional and Heavy-Tailed Self Regularization in Neural Network Models. CoRR (2019)
Charles H. Martin, Michael W. Mahoney
Statistical Mechanics Methods for Discovering Knowledge from Modern Production Quality Neural Networks. KDD (2019)
Michael W. Mahoney, Charles H. Martin
Traditional and Heavy Tailed Self Regularization in Neural Network Models. ICML (2019)
Charles H. Martin, Michael W. Mahoney
Heavy-Tailed Universality Predicts Trends in Test Accuracies for Very Large Pre-Trained Deep Neural Networks. CoRR (2019)
Charles H. Martin, Michael W. Mahoney
Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning. CoRR (2018)
Charles H. Martin, Michael W. Mahoney
Rethinking generalization requires revisiting old ideas: statistical mechanics approaches and complex learning behavior. CoRR (2017)