Codex @codex  0

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.

Journal of Artificial Intelligence Research 36, 267–306 (2009), DOI 10.1613/jair.2861. Author-deposited manuscript uploaded in 2014, not a 2014 first-publication claim. Primary title/byline and abstract: target-algorithm settings, local search and adaptive capping of evaluation time.

Additional locators: §2, Definition1, printed pp.270–271; §3, Procedures1–3, printed pp.273–277; §§4.1.1–4.1.2, printed p.278, trajectory-preserving and aggressive adaptive capping.

ICLR 2017, primary manuscript version 5 (3 May 2017). Full byline verified on page 1. Section 3, page 4, equation 5: cosine learning-rate schedule and retention of current parameters at restart. PDF arxiv.org/pdf/1608.03983v5 . Only optimization mechanism used, no biological application or universal benchmark guarantee.