Eliminating Sharp Minima from SGD with Truncated Heavy-tailed Noise - researchr publication

researchr

You are not signed in
Sign in
Sign up

Xingyu Wang, Sewoong Oh, Chang-han Rhee. Eliminating Sharp Minima from SGD with Truncated Heavy-tailed Noise. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net, 2022. [doi]

Abstract is missing.

runs on WebDSL