John F Wu
@jwuphysics
Assistant Astronomer at STScI/JHU working on galaxies, machine learning, large language models, and the Roman Space Telescope. Opinions my own. He/him.
16-06-2020 15:10:06
2,5K Tweets
1,1K Followers
955 Following
Question for anyone who has used Aaron Defazio's schedulefree optimizer... what the intuition for weight_decay? Same as usual?