{"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/non-stochastic-best-arm-identification-and","title":"Non-stochastic Best Arm Identification and Hyperparameter Optimization","arxiv_id":"1502.07943","date":"2015-02-27","proceeding":null,"authors":["Kevin Jamieson","Ameet Talwalkar"],"abstract":"Motivated by the task of hyperparameter optimization, we introduce the\nnon-stochastic best-arm identification problem. Within the multi-armed bandit\nliterature, the cumulative regret objective enjoys algorithms and analyses for\nboth the non-stochastic and stochastic settings while to the best of our\nknowledge, the best-arm identification framework has only been considered in\nthe stochastic setting. We introduce the non-stochastic setting under this\nframework, identify a known algorithm that is well-suited for this setting, and\nanalyze its behavior. Next, by leveraging the iterative nature of standard\nmachine learning algorithms, we cast hyperparameter optimization as an instance\nof non-stochastic best-arm identification, and empirically evaluate our\nproposed algorithm on this task. Our empirical results show that, by allocating\nmore resources to promising hyperparameter settings, we typically achieve\ncomparable test accuracies an order of magnitude faster than baseline methods.","url_abs":"http://arxiv.org/abs/1502.07943v1","url_pdf":"http://arxiv.org/pdf/1502.07943v1.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":"non-stochastic-best-arm-identification-and","repo_url":"https://github.com/mlr-org/mlr3hyperband","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"LGPL-3.0"}}],"tasks":[{"task_slug":"hyperparameter-optimization","task_name":"Hyperparameter Optimization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1502.07943","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}