{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T03:58:04Z","timestamp":1781063884016,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,9,22]],"date-time":"2020-09-22T00:00:00Z","timestamp":1600732800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,9,22]]},"DOI":"10.1145\/3383313.3412214","type":"proceedings-article","created":{"date-parts":[[2020,9,19]],"date-time":"2020-09-19T02:28:22Z","timestamp":1600482502000},"page":"456-461","source":"Crossref","is-referenced-by-count":24,"title":["Deep Bayesian Bandits: Exploring in Online Personalized Recommendations"],"prefix":"10.1145","author":[{"given":"Dalin","family":"Guo","sequence":"first","affiliation":[{"name":"UC San Diego, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sofia Ira","family":"Ktena","sequence":"additional","affiliation":[{"name":"Twitter, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pranay Kumar","family":"Myana","sequence":"additional","affiliation":[{"name":"Twitter, United kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ferenc","family":"Huszar","sequence":"additional","affiliation":[{"name":"Twitter, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenzhe","family":"Shi","sequence":"additional","affiliation":[{"name":"Twitter, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alykhan","family":"Tejani","sequence":"additional","affiliation":[{"name":"Twitter, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Kneier","sequence":"additional","affiliation":[{"name":"Twitter, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sourav","family":"Das","sequence":"additional","affiliation":[{"name":"Twitter, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,9,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International Conference on Machine Learning. 127\u2013135","author":"Agrawal Shipra","year":"2013"},{"key":"e_1_3_2_1_2_1","first-page":"397","article-title":"Using confidence bounds for exploitation-exploration trade-offs","author":"Auer Peter","year":"2002","journal-title":"Journal of Machine Learning Research 3"},{"key":"e_1_3_2_1_3_1","volume-title":"Finite-time analysis of the multiarmed bandit problem. Machine learning 47, 2-3","author":"Auer Peter","year":"2002"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/2567709.2567766"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240370"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623634"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics. 208\u2013214","author":"Chu Wei","year":"2011"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1080\/03610919408813175"},{"key":"e_1_3_2_1_12_1","volume-title":"international conference on machine learning. 1050\u20131059","author":"Gal Yarin","year":"2016"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159687"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3347002"},{"key":"e_1_3_2_1_15_1","volume-title":"Asymptotically efficient adaptive allocation rules. Advances in applied mathematics 6, 1","author":"Lai Tze\u00a0Leung","year":"1985"},{"key":"e_1_3_2_1_16_1","unstructured":"Balaji Lakshminarayanan Alexander Pritzel and Charles Blundell. 2017. Simple and scalable predictive uncertainty estimation using deep ensembles. In Advances in neural information processing systems. 6402\u20136413.  Balaji Lakshminarayanan Alexander Pritzel and Charles Blundell. 2017. Simple and scalable predictive uncertainty estimation using deep ensembles. In Advances in neural information processing systems. 6402\u20136413."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1935826.1935878"},{"key":"e_1_3_2_1_19_1","unstructured":"Feng Liu Ruiming Tang Xutao Li Weinan Zhang Yunming Ye Haokun Chen Huifeng Guo and Yuzhou Zhang. 2018. Deep reinforcement learning based recommendation with explicit user-item interactions modeling. arXiv preprint arXiv:1810.12027(2018).  Feng Liu Ruiming Tang Xutao Li Weinan Zhang Yunming Ye Haokun Chen Huifeng Guo and Yuzhou Zhang. 2018. Deep reinforcement learning based recommendation with explicit user-item interactions modeling. arXiv preprint arXiv:1810.12027(2018)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240354"},{"key":"e_1_3_2_1_21_1","volume-title":"Human-level control through deep reinforcement learning. Nature 518, 7540","author":"Mnih Volodymyr","year":"2015"},{"key":"e_1_3_2_1_23_1","unstructured":"Ian Osband Charles Blundell Alexander Pritzel and Benjamin Van\u00a0Roy. 2016. Deep exploration via bootstrapped DQN. In Advances in neural information processing systems. 4026\u20134034.  Ian Osband Charles Blundell Alexander Pritzel and Benjamin Van\u00a0Roy. 2016. Deep exploration via bootstrapped DQN. In Advances in neural information processing systems. 4026\u20134034."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390255"},{"key":"e_1_3_2_1_25_1","volume-title":"Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling. International Conference on Learning Representations, ICLR.","author":"Riquelme Carlos","year":"2018"},{"key":"e_1_3_2_1_26_1","unstructured":"Giorgio Roffo and Alessandro Vinciarelli. 2016. Personality in computational advertising: A benchmark. In 4 th Workshop on Emotions and Personality in Personalized Systems (EMPIRE).  Giorgio Roffo and Alessandro Vinciarelli. 2016. Personality in computational advertising: A benchmark. In 4 th Workshop on Emotions and Personality in Personalized Systems (EMPIRE)."},{"key":"e_1_3_2_1_27_1","unstructured":"Jasper Snoek Yaniv Ovadia Emily Fertig Balaji Lakshminarayanan Sebastian Nowozin D Sculley Joshua Dillon Jie Ren and Zachary Nado. 2019. Can you trust your model\u2019s uncertainty? Evaluating predictive uncertainty under dataset shift. In Advances in Neural Information Processing Systems. 13969\u201313980.  Jasper Snoek Yaniv Ovadia Emily Fertig Balaji Lakshminarayanan Sebastian Nowozin D Sculley Joshua Dillon Jie Ren and Zachary Nado. 2019. Can you trust your model\u2019s uncertainty? Evaluating predictive uncertainty under dataset shift. In Advances in Neural Information Processing Systems. 13969\u201313980."},{"key":"e_1_3_2_1_28_1","volume-title":"International conference on machine learning. 2171\u20132180","author":"Snoek Jasper","year":"2015"},{"key":"e_1_3_2_1_29_1","volume-title":"Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research 15, 1","author":"Srivastava Nitish","year":"2014"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/25.3-4.285"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3124749.3124754"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2623372","article-title":"Exploration in interactive personalized music recommendation: a reinforcement learning approach","volume":"11","author":"Wang Xinxi","year":"2014","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3316481"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. 3646\u20133653","author":"Zhou Li","year":"2016"}],"event":{"name":"RecSys '20: Fourteenth ACM Conference on Recommender Systems","location":"Virtual Event Brazil","acronym":"RecSys '20","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGAI ACM Special Interest Group on Artificial Intelligence","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval","SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGecom Special Interest Group on Economics and Computation"]},"container-title":["Fourteenth ACM Conference on Recommender Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3383313.3412214","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3383313.3412214","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:02:02Z","timestamp":1750197722000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3383313.3412214"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,22]]},"references-count":34,"alternative-id":["10.1145\/3383313.3412214","10.1145\/3383313"],"URL":"https:\/\/doi.org\/10.1145\/3383313.3412214","relation":{},"subject":[],"published":{"date-parts":[[2020,9,22]]}}}