The paper proposes decoupling weight decay from the optimization steps taken with respect to the loss function, to resolve what it describes as a limitation of common implementations of adaptive gradient algorithms such as Adam.
One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.
What it connects
Decoupled Weight Decay Regularization → states its contribution → The paper proposes decoupling weight decay from the optimization steps taken with respect to the loss function, to resolve what it describes as a limitation of common implementations of adaptive gradient algorithms such as Adam.
Where it appears
No collection page holds this claim. It is listed with its records in the explorer.