A Diffusion Theory For Deep Learning Dynamics: Stochastic Gradient Descent Exponentially Favors Flat Minima - researchr publication

researchr

You are not signed in
Sign in
Sign up

Zeke Xie, Issei Sato, Masashi Sugiyama. A Diffusion Theory For Deep Learning Dynamics: Stochastic Gradient Descent Exponentially Favors Flat Minima. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net, 2021. [doi]

Abstract is missing.

runs on WebDSL