{"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/coin-betting-and-parameter-free-online","title":"Coin Betting and Parameter-Free Online Learning","arxiv_id":"1602.04128","date":"2016-02-12","proceeding":"NeurIPS 2016 12","authors":["Francesco Orabona","Dávid Pál"],"abstract":"In the recent years, a number of parameter-free algorithms have been\ndeveloped for online linear optimization over Hilbert spaces and for learning\nwith expert advice. These algorithms achieve optimal regret bounds that depend\non the unknown competitors, without having to tune the learning rates with\noracle choices.\n  We present a new intuitive framework to design parameter-free algorithms for\n\\emph{both} online linear optimization over Hilbert spaces and for learning\nwith expert advice, based on reductions to betting on outcomes of adversarial\ncoins. We instantiate it using a betting algorithm based on the\nKrichevsky-Trofimov estimator. The resulting algorithms are simple, with no\nparameters to be tuned, and they improve or match previous results in terms of\nregret guarantee and per-round complexity.","url_abs":"http://arxiv.org/abs/1602.04128v4","url_pdf":"http://arxiv.org/pdf/1602.04128v4.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":"coin-betting-and-parameter-free-online","repo_url":"https://github.com/bremen79/parameterfree","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1602.04128","atlas_url":"https://app.syntology.ai/?focus=1602.04128","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}