= Decoupled Weight Decay Regularization by Ilya Loshchilov and Frank Hutter
{c}
{tag=Work by Ilya Loshchilov}
{tag=Work by Frank Hutter}
{title2=ICLR2019}
https://arxiv.org/abs/1711.05101v3
https://arxiv.org/pdf/1711.05101v3
Primary author manuscript, version3, revised4January2019. Verified full byline on page1: Ilya Loshchilov and Frank Hutter. Section2, propositions1–2, and AppendixA distinguish SGD coefficient rescaling from inequivalence under adaptive coordinate scaling; Algorithm2 introduces AdamW. The paper's direct shrinkage factor1-lambda and the wiki's explicitly stated PyTorch1-eta\*lambda convention must not be silently conflated. Only mathematical mechanisms used; no comparative benchmark claims.
Back to article page
