{"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/normalized-online-learning-1","title":"Normalized Online Learning","arxiv_id":"1305.6646","date":"2013-05-28","proceeding":null,"authors":["Stephane Ross","Paul Mineiro","John Langford"],"abstract":"We introduce online learning algorithms which are independent of feature\nscales, proving regret bounds dependent on the ratio of scales existent in the\ndata rather than the absolute scale. This has several useful effects: there is\nno need to pre-normalize data, the test-time and test-space complexity are\nreduced, and the algorithms are more robust.","url_abs":"http://arxiv.org/abs/1305.6646v1","url_pdf":"http://arxiv.org/pdf/1305.6646v1.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":"normalized-online-learning-1","repo_url":"https://github.com/Tiiiger/SGC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1305.6646","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}