Document · Research paper

Decoupled Weight Decay Regularization

Work-level record. Its arXiv versions and any conference or journal version are listed as sources, each with its own date. A citation to the work does not identify which version the citing author read.

Issued by

No issuing record yet. A missing record is a gap in coverage.

Authors credited

No authorship claim recorded yet. The source records list arXiv, Ilya Loshchilov and Frank Hutter.

Dates

No date claim recorded yet. The source records give the publication date as 2017-11-14.

Exact source

Decoupled Weight Decay Regularization arXiv · published 2017-11-14 · arXiv abstract page, retrieved for the candidate pack on 2026-10-28 (SHA-256 f94c66ae5bf4546e8fd5cd517d868cd12744857aee2cd1e47e86f6a44440e674). Submission history as arXiv records it (UTC): v1 14 November 2017; v2 14 February 2018; v3 4 January 2019. The page serves the latest version; each version is a separate expression, and only the one a record names was read.
Decoupled Weight Decay Regularization arXiv · published 2017-11-14 · arXiv:1711.05101v1, submitted 14 November 2017 (UTC). Retrieved for the candidate pack on 2026-10-28 (SHA-256 0da9719c9879d249dd3fd1f33dd0545cd0fd15b7fc7dc3bd333c80c1d12d4454). The author list is the byline as printed on the first page.

Appears in

No collection holds a record about this document yet.

Versions

No other versions of this document are recorded. The evidence applies to the source version listed above. Other versions, such as a preprint, working paper or journal publication, are not identified or substituted.

Documentary relations

Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.

Cited by · 5

Recorded documents that explicitly reference this one. A citation to a work does not identify which version was read.

Not recorded for this document: cites · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · discusses · reports evaluation of. A missing record does not show that the relation does not exist.

What the document says it adds

The document’s own description of its contribution, quoted from the version each row names. A claim to be the first is the document’s claim; Selekoa does not assess it.

In its own wordsThe 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.“We propose a simple way to resolve this issue by decoupling weight decay and the optimization steps taken w.r.t. the loss function.” arXiv v1, PDF p. 1, abstract2017-11-14 · publication · Stated in source · Supported Inspect claim & evidence ↗