{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mechanic-a-learning-rate-tuner","title":"Mechanic: A Learning Rate Tuner","arxiv_id":"2306.00144","date":"2023-05-31","proceeding":"NeurIPS 2023 11","authors":[],"abstract":"We introduce a technique for tuning the learning rate scale factor of any base optimization algorithm and schedule automatically, which we call \\textsc{mechanic}. Our method provides a practical realization of recent theoretical reductions for accomplishing a similar goal in online convex optimization. We rigorously evaluate \\textsc{mechanic} on a range of large scale deep learning tasks with varying batch sizes, schedules, and base optimization algorithms. These experiments demonstrate that depending on the problem, \\textsc{mechanic} either comes very close to, matches or even improves upon manual tuning of learning rates.","url_abs":"https://arxiv.org/abs/2306.00144v2","url_pdf":"https://arxiv.org/pdf/2306.00144v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mechanic-a-learning-rate-tuner","repo_url":"https://github.com/optimizedlearning/mechanic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}