{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T04:20:08Z","timestamp":1783398008478,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737086","type":"proceedings-article","created":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T13:30:13Z","timestamp":1754055013000},"page":"850-859","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Practical Contextual Bandits for Large-Scale Structured Discrete Constrained Optimization Problems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6049-7739","authenticated-orcid":false,"given":"Pavithra","family":"Harsha","sequence":"first","affiliation":[{"name":"IBM Research, Yorktown Heights, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8745-9693","authenticated-orcid":false,"given":"Chitra","family":"Subramanian","sequence":"additional","affiliation":[{"name":"IBM Research, Yorktown Heights, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4048-3989","authenticated-orcid":false,"given":"Naoki","family":"Abe","sequence":"additional","affiliation":[{"name":"IBM Research, Yorktown Heights, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8391-7321","authenticated-orcid":false,"given":"Shivaram","family":"Subramanian","sequence":"additional","affiliation":[{"name":"IBM Research, Yorktown Heights, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9259-1199","authenticated-orcid":false,"given":"Amadou","family":"Ba","sequence":"additional","affiliation":[{"name":"IBM Research, Dublin, Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7359-644X","authenticated-orcid":false,"given":"Kevin Arturo","family":"Fern\u00e1ndez Rom\u00e1n","sequence":"additional","affiliation":[{"name":"IBM CIO, Guadalajara, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7959-9086","authenticated-orcid":false,"given":"Mauricio","family":"Longinos Garrido","sequence":"additional","affiliation":[{"name":"IBM CIO, Guadalajara, Mexico"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4242-5352","authenticated-orcid":false,"given":"Chandrasekhar","family":"Narayanaswami","sequence":"additional","affiliation":[{"name":"IBM Research, Yorktown Heights, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Improved algorithms for linear stochastic bandits. Advances in neural information processing systems","author":"Abbasi-Yadkori Yasin","year":"2011","unstructured":"Yasin Abbasi-Yadkori, D\u00e1vid P\u00e1l, and Csaba Szepesv\u00e1ri. 2011. Improved algorithms for linear stochastic bandits. Advances in neural information processing systems, Vol. 24 (2011)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00453-003-1038-1"},{"key":"e_1_3_2_2_3_1","first-page":"3","article-title":"Associative reinforcement learning using linear probabilistic concepts","author":"Abe Naoki","year":"1999","unstructured":"Naoki Abe and Philip M Long. 1999. Associative reinforcement learning using linear probabilistic concepts. In ICML. Citeseer, 3-11.","journal-title":"ICML. Citeseer"},{"key":"e_1_3_2_2_4_1","unstructured":"Alekh Agarwal Sarah Bird Markus Cozowicz Luong Hoang John Langford Stephen Lee Jiaji Li Dan Melamed Gal Oshri Oswaldo Ribas et al. 2016. Making contextual decisions with low technical debt. arXiv preprint arXiv:1606.03966(2016)."},{"key":"e_1_3_2_2_5_1","first-page":"19","article-title":"Contextual bandit learning with predictable rewards","author":"Agarwal Alekh","year":"2012","unstructured":"Alekh Agarwal, Miroslav Dud\u00edk, Satyen Kale, John Langford, and Robert Schapire. 2012. Contextual bandit learning with predictable rewards. In Artificial Intelligence and Statistics. PMLR, 19-26.","journal-title":"Artificial Intelligence and Statistics. PMLR"},{"key":"e_1_3_2_2_6_1","volume-title":"International conference on machine learning. PMLR, 1638-1646","author":"Agarwal Alekh","year":"2014","unstructured":"Alekh Agarwal, Daniel Hsu, Satyen Kale, John Langford, Lihong Li, and Robert Schapire. 2014. Taming the monster: A fast and simple algorithm for contextual bandits. In International conference on machine learning. PMLR, 1638-1646."},{"key":"e_1_3_2_2_7_1","volume-title":"International conference on machine learning. PMLR, 127-135","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, 127-135."},{"key":"e_1_3_2_2_8_1","volume-title":"Martin WP Savelsbergh, and Pamela H Vance","author":"Barnhart Cynthia","year":"1998","unstructured":"Cynthia Barnhart, Ellis L Johnson, George L Nemhauser, Martin WP Savelsbergh, and Pamela H Vance. 1998. Branch-and-price: Column generation for solving huge integer programs. Operations research, Vol. 46, 3 (1998), 316-329."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2019.1902"},{"key":"e_1_3_2_2_10_1","first-page":"623","volume-title":"17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Bhardwaj Romil","year":"2023","unstructured":"Romil Bhardwaj, Kirthevasan Kandasamy, Asim Biswal, Wenshuo Guo, Benjamin Hindman, Joseph Gonzalez, Michael Jordan, and Ion Stoica. 2023. Cilantro: Performance-Aware resource allocation for general objectives via online feedback. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23). 623-643."},{"key":"e_1_3_2_2_11_1","first-page":"1","article-title":"A contextual bandit bake-off","volume":"22","author":"Bietti Alberto","year":"2021","unstructured":"Alberto Bietti, Alekh Agarwal, and John Langford. 2021. A contextual bandit bake-off. Journal of Machine Learning Research, Vol. 22, 133 (2021), 1-49.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05983-y"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.1050.0133"},{"key":"e_1_3_2_2_14_1","unstructured":"CPLEX. [n.d.]. CPLEX Solution Pool. https:\/\/www.ibm.com\/docs\/en\/icos\/22.1.2?topic=solutions-what-is-solution-pool."},{"key":"e_1_3_2_2_15_1","first-page":"3","article-title":"Stochastic Linear Optimization under Bandit Feedback","volume":"2","author":"Dani Varsha","year":"2008","unstructured":"Varsha Dani, Thomas P Hayes, and Sham M Kakade. 2008. Stochastic Linear Optimization under Bandit Feedback.. In COLT, Vol. 2. 3.","journal-title":"COLT"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.2016.0714"},{"key":"e_1_3_2_2_17_1","unstructured":"Miroslav Dudik Daniel Hsu Satyen Kale Nikos Karampatziakis John Langford Lev Reyzin and Tong Zhang. 2011. Efficient optimal learning for contextual bandits. arXiv preprint arXiv:1106.2369(2011)."},{"key":"e_1_3_2_2_18_1","volume-title":"Bin Hong Alex Lee, and David Simchi-Levi","author":"Ferreira Kris Johnson","year":"2016","unstructured":"Kris Johnson Ferreira, Bin Hong Alex Lee, and David Simchi-Levi. 2016. Analytics for an online retailer: Demand forecasting and price optimization. Manufacturing & service operations management, Vol. 18, 1 (2016), 69-88."},{"key":"e_1_3_2_2_19_1","volume-title":"International Conference on Machine Learning. PMLR, 1539-1548","author":"Foster Dylan","year":"2018","unstructured":"Dylan Foster, Alekh Agarwal, Miroslav Dud\u00edk, Haipeng Luo, and Robert Schapire. 2018. Practical contextual bandits with regression oracles. In International Conference on Machine Learning. PMLR, 1539-1548."},{"key":"e_1_3_2_2_20_1","volume-title":"International Conference on Machine Learning. PMLR, 3199-3210","author":"Foster Dylan","year":"2020","unstructured":"Dylan Foster and Alexander Rakhlin. 2020. Beyond ucb: Optimal and efficient contextual bandits with regression oracles. In International Conference on Machine Learning. PMLR, 3199-3210."},{"key":"e_1_3_2_2_21_1","first-page":"18907","article-title":"Efficient first-order contextual bandits: Prediction, allocation, and triangular discrimination","volume":"34","author":"Foster Dylan J","year":"2021","unstructured":"Dylan J Foster and Akshay Krishnamurthy. 2021. Efficient first-order contextual bandits: Prediction, allocation, and triangular discrimination. Advances in Neural Information Processing Systems, Vol. 34 (2021), 18907-18919.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_22_1","unstructured":"Gurobi. [n.d.]. Gurobi Solution Pool. https:\/\/docs.gurobi.com\/projects\/optimizer\/en\/current\/features\/solutionpool.html#solution-pool."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1287\/ijoo.2019.0018"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-25486-2_2"},{"key":"e_1_3_2_2_25_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Jun Kwang-Sung","year":"2017","unstructured":"Kwang-Sung Jun, Aniruddha Bhargava, Robert Nowak, and Rebecca Willett. 2017. Scalable generalized linear bandits: Online computation and hashing. Advances in Neural Information Processing Systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_26_1","first-page":"1","article-title":"Contextual bandits with continuous actions: Smoothing, zooming, and adapting","volume":"21","author":"Krishnamurthy Akshay","year":"2020","unstructured":"Akshay Krishnamurthy, John Langford, Aleksandrs Slivkins, and Chicheng Zhang. 2020. Contextual bandits with continuous actions: Smoothing, zooming, and adapting. Journal of Machine Learning Research, Vol. 21, 137 (2020), 1-45.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"e_1_3_2_2_28_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Li Lihong","year":"2017","unstructured":"Lihong Li, Yu Lu, and Dengyong Zhou. 2017. Provably optimal algorithms for generalized linear contextual bandits. In International Conference on Machine Learning. PMLR, 2071-2080."},{"key":"e_1_3_2_2_29_1","first-page":"805","volume-title":"14th USENIX symposium on operating systems design and implementation (OSDI 20)","author":"Qiu Haoran","year":"2020","unstructured":"Haoran Qiu, Subho S Banerjee, Saurabh Jha, Zbigniew T Kalbarczyk, and Ravishankar K Iyer. 2020. {FIRM}: An intelligent fine-grained resource management framework for {SLO-Oriented} microservices. In 14th USENIX symposium on operating systems design and implementation (OSDI 20). 805-825."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1561\/9781680834710"},{"key":"e_1_3_2_2_31_1","volume-title":"International Conference on Machine Learning. PMLR, 9422-9433","author":"Sen Rajat","year":"2021","unstructured":"Rajat Sen, Alexander Rakhlin, Lexing Ying, Rahul Kidambi, Dean Foster, Daniel N Hill, and Inderjit S Dhillon. 2021. Top-k extreme contextual bandits with arm hierarchy. In International Conference on Machine Learning. PMLR, 9422-9433."},{"key":"e_1_3_2_2_32_1","first-page":"403","volume-title":"2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Shi Jiuchen","year":"2023","unstructured":"Jiuchen Shi, Hang Zhang, Zhixin Tong, Quan Chen, Kaihua Fu, and Minyi Guo. 2023. Nodens: Enabling Resource Efficient and Fast {QoS} Recovery of Dynamic Microservice Applications in Datacenters. In 2023 USENIX Annual Technical Conference (USENIX ATC 23). 403-417."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2021.1193"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.1080.0267"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20384"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Ambuj Tewari and Susan A Murphy. 2017. From ads to interventions: Contextual bandits in mobile health. Mobile health: sensors analytic methods and applications(2017) 495-517.","DOI":"10.1007\/978-3-319-51394-2_25"},{"key":"e_1_3_2_2_37_1","volume-title":"International Conference on Machine Learning. PMLR, 25241-25260","author":"Yang Shuo","year":"2022","unstructured":"Shuo Yang, Tongzheng Ren, Sanjay Shakkottai, Eric Price, Inderjit S Dhillon, and Sujay Sanghavi. 2022. Linear bandit algorithms with sublinear time complexity. In International Conference on Machine Learning. PMLR, 25241-25260."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00077"},{"key":"e_1_3_2_2_39_1","volume-title":"International Conference on Machine Learning. PMLR, 27428-27453","author":"Zhu Yinglun","year":"2022","unstructured":"Yinglun Zhu, Dylan J Foster, John Langford, and Paul Mineiro. 2022. Contextual bandits with large action spaces: Made practical. In International Conference on Machine Learning. PMLR, 27428-27453."},{"key":"e_1_3_2_2_40_1","volume-title":"International Conference on Machine Learning. PMLR, 27574-27590","author":"Zhu Yinglun","year":"2022","unstructured":"Yinglun Zhu and Paul Mineiro. 2022. Contextual bandits with smooth regret: Efficient learning in continuous action spaces. In International Conference on Machine Learning. PMLR, 27574-27590."}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3737086","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:54:02Z","timestamp":1777571642000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737086"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":40,"alternative-id":["10.1145\/3711896.3737086","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737086","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}