Author of the publication

On the Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural Networks

, , , , and . (2019)cite arxiv:1912.00018Comment: 32 pages. arXiv admin note: substantial text overlap with arXiv:1901.06053.

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.

 

Other publications of authors with the same name

Empirical Analysis of the Hessian of Over-Parametrized Neural Networks., , , , and . CoRR, (2017)Empirical Analysis of the Hessian of Over-Parametrized Neural Networks, , , , and . (2017)cite arxiv:1706.04454Comment: Minor update for ICLR 2018 Workshop Track presentation.Confusing Large Models by Confusing Small Models., , , , , and . ICCV (Workshops), page 4306-4314. IEEE, (2023)Triple descent and the two kinds of overfitting: where & why do they appear?, , and . NeurIPS, (2020)On the interplay between data structure and loss function in classification problems., , , and . NeurIPS, page 8506-8517. (2021)ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases., , , , , and . ICML, volume 139 of Proceedings of Machine Learning Research, page 2286-2296. PMLR, (2021)Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond, , and . arXiv preprint arXiv:1611.07476, (2016)Easing non-convex optimization with neural networks., and . ICLR (Workshop), OpenReview.net, (2018)A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks, , and . (2019)cite arxiv:1901.06053.Measuring and signing fairness as performance under multiple stakeholder distributions., , , and . CoRR, (2022)