( en | de | ru )

 

Disambiguation of "Martin, Charles H."

Author of the publication

copydeleteadd this publication to your clipboard
Rethinking generalization requires revisiting old ideas: statistical mechanics approaches and complex learning behavior

, and . (2017)cite arxiv:1710.09553Comment: 31 pages; added brief discussion of recent papers that use/extend these ideas.

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed. You can also use the button next to the name to display some publications already assigned to the person.

Charles H Watkins

Martin H Trauth

Martin H Ofner

Martin H Wenderoth

Martin H Trauth

 

Other publications of authors with the same name

Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning., and . CoRR, (2018)Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning., and . J. Mach. Learn. Res., (2021)Test Accuracy vs. Generalization Gap: Model Selection in NLP without Accessing Training or Testing Data., , , , , , and . KDD, page 3011-3021. ACM, (2023)Statistical Mechanics Methods for Discovering Knowledge from Modern Production Quality Neural Networks., and . KDD, page 3239-3240. ACM, (2019)Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data., , and . CoRR, (2020)Post-mortem on a deep learning contest: a Simpson's paradox and the complementary roles of scale metrics versus shape metrics., and . CoRR, (2021)Heavy-Tailed Universality Predicts Trends in Test Accuracies for Very Large Pre-Trained Deep Neural Networks., and . SDM, page 505-513. SIAM, (2020)The conference was canceled because of the coronavirus pandemic, the reviewed papers are published in this volume..Rethinking generalization requires revisiting old ideas: statistical mechanics approaches and complex learning behavior, and . (2017)cite arxiv:1710.09553Comment: 31 pages; added brief discussion of recent papers that use/extend these ideas.Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data., , , , , , and . CoRR, (2022)Heavy-Tailed Universality Predicts Trends in Test Accuracies for Very Large Pre-Trained Deep Neural Networks., and . CoRR, (2019)