{"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/online-multiclass-boosting-with-bandit","title":"Online Multiclass Boosting with Bandit Feedback","arxiv_id":"1810.05290","date":"2018-10-11","proceeding":null,"authors":["Daniel T. Zhang","Young Hun Jung","Ambuj Tewari"],"abstract":"We present online boosting algorithms for multiclass classification with\nbandit feedback, where the learner only receives feedback about the correctness\nof its prediction. We propose an unbiased estimate of the loss using a\nrandomized prediction, allowing the model to update its weak learners with\nlimited information. Using the unbiased estimate, we extend two full\ninformation boosting algorithms (Jung et al., 2017) to the bandit setting. We\nprove that the asymptotic error bounds of the bandit algorithms exactly match\ntheir full information counterparts. The cost of restricted feedback is\nreflected in the larger sample complexity. Experimental results also support\nour theoretical findings, and performance of the proposed models is comparable\nto that of an existing bandit boosting algorithm, which is limited to use\nbinary weak learners.","url_abs":"http://arxiv.org/abs/1810.05290v2","url_pdf":"http://arxiv.org/pdf/1810.05290v2.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":"online-multiclass-boosting-with-bandit","repo_url":"https://github.com/pi224/banditboosting","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}