论文 ID ATH-K7VBQA
· 一区论文
· 计算机科学
AutoResearch Lite: a reproducible paper-inspired experiment runner (Adam mechanism reproduction and convergence-speed comparison) CC-BY
这是一篇从 DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) 导入的开放获取论文,用于长期保存;它并非本站投稿,因此不设版本历史与时间戳历史。
- 原出版日期:2026年1月1日 UTC
- 权利状态:CC-BY(未记录届满日期)
- 加入本站:2026年10月3日 UTC
由以下人员代作者上传 AthenXiv (UW2JTS24Y)
摘要
A dependency-free experiment runner that turns a paper's research question into a configuration-driven, verifiable experiment task. The bundled reproduction maps the first/second moment estimates and bias correction of Adam (Kingma & Ba, arXiv:1412.6980) into runnable Python and compares them against fixed-learning-rate SGD under fixed seeds and epoch budgets. A second experiment measures convergence speed (epochs to reach a target training loss) against SGD with heavy-ball momentum, AdaGrad and RMSProp, with every optimizer family tuned by the same coarse learning-rate sweep. In that experiment Adam is not the fastest; the negative result is reported in full. Every reported number is pinned in an expected-values file with explicit tolerances and checked by one command that also runs the unit tests, and the checking harness is validated against deliberately broken implementations (negative controls). The repository also ships a task contract that expresses the reproduction as a repeatable, scoreable task for an automated research loop.
关键词: Stochastic Gradient Optimization Techniques, Artificial Intelligence, Computer Science, Physical Sciences
DOI: 10.4230/oasics.dx.2026.15
许可协议: CC-BY
在线阅读
外部链接
- DOI DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.DNA.28.4
引用本文
Antoni Rogowski, Anna Sztyber (2026).
AutoResearch Lite: a reproducible paper-inspired experiment runner (Adam mechanism reproduction and convergence-speed comparison). AthenXiv.
https://athenxiv.com/paper/ATH-K7VBQA