https://arxiv.org/abs/1803.05407 "Averaging Weights Leads to Wider Optima and Be... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

sillysaurusx on Jan 9, 2020 | parent | context | favorite | on: An idea from physics helps AI see in higher dimens...

https://arxiv.org/abs/1803.05407

"Averaging Weights Leads to Wider Optima and Better Generalization"

Weirdly, the averaging doesn't have to be synchronous.

Consider applying for YC's Spring batch! Applications are open till Feb 11.
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact