AdamW optimizer introduced in paper: Decoupled Weight Decay Regularization (Loshchilov & Hutter, 2017).
Predicate
introduced_in_paper
Object
Decoupled Weight Decay Regularization (Loshchilov & Hutter, 2017)
Primary source · preprint · 2017-11-14
Decoupled Weight Decay Regularization — arXiv (Loshchilov, Hutter)