{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:10:15Z","timestamp":1750219815222,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T00:00:00Z","timestamp":1694649600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-23-1-0030"],"award-info":[{"award-number":["W911NF-23-1-0030"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2007492, 2128019, 1838615"],"award-info":[{"award-number":["2007492, 2128019, 1838615"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,9,14]]},"DOI":"10.1145\/3604915.3608794","type":"proceedings-article","created":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T22:40:23Z","timestamp":1694731223000},"page":"415-425","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Incentivizing Exploration in Linear Contextual Bandits under Information Gap"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3918-6925","authenticated-orcid":false,"given":"Huazheng","family":"Wang","sequence":"first","affiliation":[{"name":"Oregon State University, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6371-4906","authenticated-orcid":false,"given":"Haifeng","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Chicago, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2440-0596","authenticated-orcid":false,"given":"Chuanhao","family":"Li","sequence":"additional","affiliation":[{"name":"University of Virginia, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4356-4183","authenticated-orcid":false,"given":"Zhiyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Colorado,Boulder, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6524-9195","authenticated-orcid":false,"given":"Hongning","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Virginia, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,9,14]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Yasin Abbasi-yadkori D\u00e1vid P\u00e1l and Csaba Szepesv\u00e1ri. 2011. Improved Algorithms for Linear Stochastic Bandits. In NIPS. 2312\u20132320."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Marc Abeille and Alessandro Lazaric. 2017. Linear thompson sampling revisited. In Artificial Intelligence and Statistics. PMLR 176\u2013184.","DOI":"10.1214\/17-EJS1341SI"},{"volume-title":"Multi-Agent Systems and Agreement Technologies","author":"Agrawal Priyank","key":"e_1_3_2_1_3_1","unstructured":"Priyank Agrawal and Theja Tulabandhula. 2020. Incentivising Exploration and Recommendations for Contextual Bandits with Payments. In Multi-Agent Systems and Agreement Technologies. Springer, 159\u2013170."},{"key":"e_1_3_2_1_4_1","volume-title":"International Conference on Machine Learning. PMLR, 127\u2013135","author":"Agrawal Shipra","year":"2013","unstructured":"Shipra Agrawal and Navin Goyal. 2013. Thompson sampling for contextual bandits with linear payoffs. In International Conference on Machine Learning. PMLR, 127\u2013135."},{"key":"e_1_3_2_1_5_1","first-page":"397","article-title":"Using Confidence Bounds for Exploitation-Exploration Trade-offs","volume":"3","author":"Auer Peter","year":"2002","unstructured":"Peter Auer. 2002. Using Confidence Bounds for Exploitation-Exploration Trade-offs. Journal of Machine Learning Research 3 (2002), 397\u2013422.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_6_1","volume-title":"Finite-time analysis of the multiarmed bandit problem. Machine learning 47, 2-3","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 47, 2-3 (2002), 235\u2013256."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2488388.2488401"},{"key":"e_1_3_2_1_8_1","unstructured":"Nicolo Cesa-Bianchi Claudio Gentile and Giovanni Zappella. 2013. A gang of bandits. In Advances in Neural Information Processing Systems. 737\u2013745."},{"key":"e_1_3_2_1_9_1","unstructured":"Olivier Chapelle and Lihong Li. 2011. An empirical evaluation of thompson sampling. In Advances in neural information processing systems. 2249\u20132257."},{"key":"e_1_3_2_1_10_1","volume-title":"Conference On Learning Theory. PMLR, 798\u2013818","author":"Chen Bangrui","year":"2018","unstructured":"Bangrui Chen, Peter Frazier, and David Kempe. 2018. Incentivizing exploration by heterogeneous users. In Conference On Learning Theory. PMLR, 798\u2013818."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3546758"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics. 208\u2013214","author":"Chu Wei","year":"2011","unstructured":"Wei Chu, Lihong Li, Lev Reyzin, and Robert Schapire. 2011. Contextual bandits with linear payoff functions. In Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics. 208\u2013214."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600057.2602897"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412214"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11874"},{"key":"e_1_3_2_1_17_1","volume-title":"Incentivizing Exploration with Selective Data Disclosure. arXiv preprint arXiv:1811.06026","author":"Immorlica Nicole","year":"2018","unstructured":"Nicole Immorlica, Jieming Mao, Aleksandrs Slivkins, and Zhiwei\u00a0Steven Wu. 2018. Incentivizing Exploration with Selective Data Disclosure. arXiv preprint arXiv:1811.06026 (2018)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474247"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3033274.3085154"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1086\/676597"},{"key":"e_1_3_2_1_21_1","volume-title":"Asymptotically efficient adaptive allocation rules. Advances in applied mathematics 6, 1","author":"Lai Tze\u00a0Leung","year":"1985","unstructured":"Tze\u00a0Leung Lai and Herbert Robbins. 1985. Asymptotically efficient adaptive allocation rules. Advances in applied mathematics 6, 1 (1985), 4\u201322."},{"key":"e_1_3_2_1_22_1","volume-title":"Stochastic linear bandits with hidden low rank structure. arXiv preprint arXiv:1901.09490","author":"Lale Sahin","year":"2019","unstructured":"Sahin Lale, Kamyar Azizzadenesheli, Anima Anandkumar, and Babak Hassibi. 2019. Stochastic linear bandits with hidden low rank structure. arXiv preprint arXiv:1901.09490 (2019)."},{"key":"e_1_3_2_1_23_1","unstructured":"Tor Lattimore and Csaba Szepesvari. 2017. The end of optimism? an asymptotic analysis of finite-armed linear bandits. In Artificial Intelligence and Statistics. PMLR 728\u2013737."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5937"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380130"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2764468.2764508"},{"key":"e_1_3_2_1_28_1","volume-title":"Sample complexity of incentivized exploration. arXiv preprint arXiv:2002.00558","author":"Sellke Mark","year":"2020","unstructured":"Mark Sellke and Aleksandrs Slivkins. 2020. Sample complexity of incentivized exploration. arXiv preprint arXiv:2002.00558 (2020)."},{"key":"e_1_3_2_1_29_1","volume-title":"Exploration and incentives in reinforcement learning. arXiv preprint arXiv:2103.00360","author":"Simchowitz Max","year":"2021","unstructured":"Max Simchowitz and Aleksandrs Slivkins. 2021. Exploration and incentives in reinforcement learning. arXiv preprint arXiv:2103.00360 (2021)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123744"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298483.3298627"},{"key":"e_1_3_2_1_32_1","unstructured":"Siwei Wang and Longbo Huang. 2018. Multi-armed Bandits with Compensation. In NeurIPS."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/1835449.1835537"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2911528"}],"event":{"name":"RecSys '23: Seventeenth ACM Conference on Recommender Systems","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"],"location":"Singapore Singapore","acronym":"RecSys '23"},"container-title":["Proceedings of the 17th ACM Conference on Recommender Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604915.3608794","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3604915.3608794","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:06Z","timestamp":1750178766000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604915.3608794"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,14]]},"references-count":34,"alternative-id":["10.1145\/3604915.3608794","10.1145\/3604915"],"URL":"https:\/\/doi.org\/10.1145\/3604915.3608794","relation":{},"subject":[],"published":{"date-parts":[[2023,9,14]]},"assertion":[{"value":"2023-09-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}