Charles H. Martin

Orcid: 0009-0004-5320-9972

According to our database1, Charles H. Martin authored at least 10 papers between 2017 and 2023.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2023
Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Test Accuracy vs. Generalization Gap: Model Selection in NLP without Accessing Training or Testing Data.
Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023

2022
Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data.
CoRR, 2022

2021
Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning.
J. Mach. Learn. Res., 2021

Post-mortem on a deep learning contest: a Simpson's paradox and the complementary roles of scale metrics versus shape metrics.
CoRR, 2021

2020
Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data.
CoRR, 2020

Heavy-Tailed Universality Predicts Trends in Test Accuracies for Very Large Pre-Trained Deep Neural Networks.
Proceedings of the 2020 SIAM International Conference on Data Mining, 2020

2019
Statistical Mechanics Methods for Discovering Knowledge from Modern Production Quality Neural Networks.
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019

Traditional and Heavy Tailed Self Regularization in Neural Network Models.
Proceedings of the 36th International Conference on Machine Learning, 2019

2017
Rethinking generalization requires revisiting old ideas: statistical mechanics approaches and complex learning behavior.
CoRR, 2017


  Loading...