Web: http://arxiv.org/abs/2204.01365

June 20, 2022, 1:11 a.m. | Carmina Fjellström, Kaj Nyström

cs.LG updates on arXiv.org arxiv.org

Stochastic gradient descent (SGD) is widely used in deep learning due to its
computational efficiency, but a complete understanding of why SGD performs so
well remains a major challenge. It has been observed empirically that most
eigenvalues of the Hessian of the loss functions on the loss landscape of
over-parametrized deep neural networks are close to zero, while only a small
number of eigenvalues are large. Zero eigenvalues indicate zero diffusion along
the corresponding directions. This indicates that the process …

arxiv deep deep learning gradient learning maps ml stochastic

More from arxiv.org / cs.LG updates on arXiv.org

Machine Learning Researcher - Saalfeld Lab

@ Howard Hughes Medical Institute - Chevy Chase, MD | Ashburn, Virginia

Project Director, Machine Learning in US Health

@ ideas42.org | Remote, US

Data Science Intern

@ NannyML | Remote

Machine Learning Engineer NLP/Speech

@ Play.ht | Remote

Research Scientist, 3D Reconstruction

@ Yembo | Remote, US

Clinical Assistant or Associate Professor of Management Science and Systems

@ University at Buffalo | Buffalo, NY