{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:03:36Z","timestamp":1750309416094,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Tencent Rhino-Bird Research Elite Program","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,21]]},"DOI":"10.1145\/3627673.3680040","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T19:34:11Z","timestamp":1729452851000},"page":"4645-4652","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Sequential Optimum Test with Multi-armed Bandits for Online Experimentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8148-8911","authenticated-orcid":false,"given":"Fang","family":"Kong","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6840-5343","authenticated-orcid":false,"given":"Penglei","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tencent Inc., Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1217-3966","authenticated-orcid":false,"given":"Shichao","family":"Han","sequence":"additional","affiliation":[{"name":"Tencent Inc., Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4464-352X","authenticated-orcid":false,"given":"Yong","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent Inc., Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3935-0708","authenticated-orcid":false,"given":"Shuai","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the 16th International Conference on Artificial Intelligence and Statistics. 99--107","author":"Agrawal Shipra","year":"2013","unstructured":"Shipra Agrawal and Navin Goyal. 2013. Further optimal regret bounds for thompson sampling. In Proceedings of the 16th International Conference on Artificial Intelligence and Statistics. 99--107."},{"key":"e_1_3_2_1_2_1","volume-title":"Conference on Learning Theory. 41--53","author":"Audibert Jean-Yves","year":"2010","unstructured":"Jean-Yves Audibert, S\u00e9bastien Bubeck, and R\u00e9mi Munos. 2010. Best arm identification in multi-armed bandits.. In Conference on Learning Theory. 41--53."},{"key":"e_1_3_2_1_3_1","volume-title":"Finite-time analysis of the multiarmed bandit problem. Machine learning","author":"Auer Peter","year":"2002","unstructured":"Peter Auer, Nicolo Cesa-Bianchi, and Paul Fischer. 2002. Finite-time analysis of the multiarmed bandit problem. Machine learning, Vol. 47, 2 (2002), 235--256."},{"key":"e_1_3_2_1_4_1","first-page":"28548","article-title":"Post-contextual-bandit inference","volume":"34","author":"Bibaut Aur\u00e9lien","year":"2021","unstructured":"Aur\u00e9lien Bibaut, Maria Dimakopoulou, Nathan Kallus, Antoine Chambaz, and Mark van Der Laan. 2021. Post-contextual-bandit inference. Advances in Neural Information Processing Systems, Vol. 34 (2021), 28548--28559.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_5_1","volume-title":"On the optimal sample complexity for best arm identification. arXiv preprint arXiv:1511.03774","author":"Chen Lijie","year":"2015","unstructured":"Lijie Chen and Jian Li. 2015. On the optimal sample complexity for best arm identification. arXiv preprint arXiv:1511.03774 (2015)."},{"key":"e_1_3_2_1_6_1","volume-title":"Conference on Learning Theory. PMLR, 1643--1646","author":"Chen Lijie","year":"2016","unstructured":"Lijie Chen and Jian Li. 2016. Open problem: Best arm identification: Almost instance-wise optimality and the gap entropy conjecture. In Conference on Learning Theory. PMLR, 1643--1646."},{"key":"e_1_3_2_1_7_1","unstructured":"Carroll Croarkin Paul Tobias JJ Filliben Barry Hembree Will Guthrie et al. 2006. NIST\/SEMATECH e-handbook of statistical methods. NIST\/SEMATECH July. Available online: http:\/\/www. itl. nist. gov\/div898\/handbook (2006) 24."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA.2016.33"},{"key":"e_1_3_2_1_9_1","first-page":"1939","article-title":"Online multi-armed bandits with adaptive inference","volume":"34","author":"Dimakopoulou Maria","year":"2021","unstructured":"Maria Dimakopoulou, Zhimei Ren, and Zhengyuan Zhou. 2021. Online multi-armed bandits with adaptive inference. Advances in Neural Information Processing Systems, Vol. 34 (2021), 1939--1951.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45435-7_18"},{"key":"e_1_3_2_1_11_1","article-title":"Action elimination and stopping conditions for the multi-armed bandit and reinforcement learning problems","volume":"7","author":"Even-Dar Eyal","year":"2006","unstructured":"Eyal Even-Dar, Shie Mannor, Yishay Mansour, and Sridhar Mahadevan. 2006. Action elimination and stopping conditions for the multi-armed bandit and reinforcement learning problems. Journal of Machine Learning Research, Vol. 7, 6 (2006).","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_12_1","volume-title":"A tutorial on testing hypotheses using the Bayes factor. Psychological methods","author":"Hoijtink Herbert","year":"2019","unstructured":"Herbert Hoijtink, Joris Mulder, Caspar van Lissa, and Xin Gu. 2019. A tutorial on testing hypotheses using the Bayes factor. Psychological methods, Vol. 24, 5 (2019), 539."},{"key":"e_1_3_2_1_13_1","article-title":"lil' UCB : An optimal exploration algorithm for multi-armed bandits","volume":"35","author":"Jamieson Kevin","year":"2013","unstructured":"Kevin Jamieson, Matthew Malloy, Robert Nowak, and S\u00e9bastien Bubeck. 2013. lil' UCB : An optimal exploration algorithm for multi-armed bandits. Journal of Machine Learning Research, Vol. 35 (12 2013).","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CISS.2014.6814096"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3097992"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2021.2135"},{"key":"e_1_3_2_1_17_1","unstructured":"Kwang-Sung Jun Kevin Jamieson Robert Nowak and Xiaojin Zhu. 2016. Top arm identification in multi-armed bandits with batch arm pulls. In Artificial Intelligence and Statistics. PMLR 139--148."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.2946646"},{"volume-title":"Trustworthy online controlled experiments: A practical guide to a\/b testing","author":"Kohavi Ron","key":"e_1_3_2_1_19_1","unstructured":"Ron Kohavi, Diane Tang, and Ya Xu. 2020. Trustworthy online controlled experiments: A practical guide to a\/b testing. Cambridge University Press."},{"volume-title":"Bandit algorithms","author":"Lattimore Tor","key":"e_1_3_2_1_20_1","unstructured":"Tor Lattimore and Csaba Szepesv\u00e1ri. 2020. Bandit algorithms. Cambridge University Press."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2023.3288988"},{"key":"e_1_3_2_1_22_1","volume-title":"A sequential procedure for selecting the population with the largest mean from k normal populations. The Annals of Mathematical Statistics","author":"Paulson Edward","year":"1964","unstructured":"Edward Paulson. 1964. A sequential procedure for selecting the population with the largest mean from k normal populations. The Annals of Mathematical Statistics (1964), 174--180."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.22237\/jmasm\/1257035100"},{"volume-title":"Sequential tests of statistical hypotheses","author":"Wald Abraham","key":"e_1_3_2_1_24_1","unstructured":"Abraham Wald. 1992. Sequential tests of statistical hypotheses. Springer."},{"key":"e_1_3_2_1_25_1","volume-title":"Optimum character of the sequential probability ratio test. The Annals of Mathematical Statistics","author":"Wald Abraham","year":"1948","unstructured":"Abraham Wald and Jacob Wolfowitz. 1948. Optimum character of the sequential probability ratio test. The Annals of Mathematical Statistics (1948), 326--339."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539144"}],"event":{"name":"CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Boise ID USA","acronym":"CIKM '24"},"container-title":["Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3680040","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627673.3680040","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:17Z","timestamp":1750294697000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3680040"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":26,"alternative-id":["10.1145\/3627673.3680040","10.1145\/3627673"],"URL":"https:\/\/doi.org\/10.1145\/3627673.3680040","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"2024-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}