AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (ICLR 2021)
Why do you think that https://github.com/jh-jeong/ContraD is a good alternative to AdamP
AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (ICLR 2021)
Why do you think that https://github.com/jh-jeong/ContraD is a good alternative to AdamP