{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T17:52:38Z","timestamp":1790358758271,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T00:00:00Z","timestamp":1728345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,8]]},"DOI":"10.1145\/3640457.3688099","type":"proceedings-article","created":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T15:39:28Z","timestamp":1728401968000},"page":"733-741","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Effective Off-Policy Evaluation and Learning in Contextual Combinatorial Bandits"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9746-3346","authenticated-orcid":false,"given":"Tatsuhiro","family":"Shimizu","sequence":"first","affiliation":[{"name":"Independent Researcher, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4790-5092","authenticated-orcid":false,"given":"Koichi","family":"Tanaka","sequence":"additional","affiliation":[{"name":"Department of Electronics and Electrical Engineering, Keio Univercity, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7443-5325","authenticated-orcid":false,"given":"Ren","family":"Kishimoto","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering and Economics, Tokyo Institute of Technology, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6378-4365","authenticated-orcid":false,"given":"Haruka","family":"Kiyohara","sequence":"additional","affiliation":[{"name":"Computer Science, Cornell University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4945-5984","authenticated-orcid":false,"given":"Masahiro","family":"Nomura","sequence":"additional","affiliation":[{"name":"CyberAgent, Inc., Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4357-5835","authenticated-orcid":false,"given":"Yuta","family":"Saito","sequence":"additional","affiliation":[{"name":"Computer Science, Cornell University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,8]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557040"},{"key":"e_1_3_2_2_2_1","volume-title":"International conference on machine learning. PMLR, PMLR","author":"Chen Wei","year":"2013","unstructured":"Wei Chen, Yajun Wang, and Yang Yuan. 2013. Combinatorial multi-armed bandit: General framework and applications. In International conference on machine learning. PMLR, PMLR, Atlanta, Georgia, USA, 151\u2013159."},{"key":"e_1_3_2_2_3_1","volume-title":"Cross-Validated Off-Policy Evaluation. arXiv preprint arXiv:2405.15332","author":"Cief Matej","year":"2024","unstructured":"Matej Cief, Michal Kompan, and Branislav Kveton. 2024. Cross-Validated Off-Policy Evaluation. arXiv preprint arXiv:2405.15332 (2024)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1214\/14-STS500"},{"key":"e_1_3_2_2_5_1","volume-title":"Proceedings of the 28th International Conference on Machine Learning. PMLR","author":"Dud\u00edk Miroslav","year":"2011","unstructured":"Miroslav Dud\u00edk, John Langford, and Lihong Li. 2011. Doubly robust policy evaluation and learning. In Proceedings of the 28th International Conference on Machine Learning. PMLR, Bellevue, WA, USA, 1097\u20131104."},{"key":"e_1_3_2_2_6_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning, Vol.\u00a080","author":"Farajtabar Mehrdad","year":"2018","unstructured":"Mehrdad Farajtabar, Yinlam Chow, and Mohammad Ghavamzadeh. 2018. More Robust Doubly Robust Off-Policy Evaluation. In Proceedings of the 35th International Conference on Machine Learning, Vol.\u00a080. PMLR, PMLR, Stockholm, Sweden, 1447\u20131456."},{"key":"e_1_3_2_2_7_1","volume-title":"AutoOPE: Automated Off-Policy Estimator Selection. arXiv preprint arXiv:2406.18022","author":"Felicioni Nicol\u00f2","year":"2024","unstructured":"Nicol\u00f2 Felicioni, Michael Benigni, and Maurizio\u00a0Ferrari Dacrema. 2024. AutoOPE: Automated Off-Policy Estimator Selection. arXiv preprint arXiv:2406.18022 (2024)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557220"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1952.10483446"},{"key":"e_1_3_2_2_10_1","volume-title":"Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation. In The Twelfth International Conference on Learning Representations.","author":"Kiyohara Haruka","year":"2024","unstructured":"Haruka Kiyohara, Ren Kishimoto, Kosuke Kawakami, Ken Kobayashi, Kazuhide Nakata, and Yuta Saito. 2024. Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645343"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498380"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599447"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220028"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403229"},{"key":"e_1_3_2_2_16_1","first-page":"8119","article-title":"Subgaussian and Differentiable Importance Sampling for Off-Policy Evaluation and Learning","volume":"34","author":"Metelli Alberto\u00a0Maria","year":"2021","unstructured":"Alberto\u00a0Maria Metelli, Alessio Russo, and Marcello Restelli. 2021. Subgaussian and Differentiable Importance Sampling for Off-Policy Evaluation and Learning. Advances in Neural Information Processing Systems 34 (2021), 8119\u20138132.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973440.53"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645501"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645446"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3473320"},{"key":"e_1_3_2_2_21_1","volume-title":"International Conference on Machine Learning. PMLR, PMLR","author":"Saito Yuta","year":"2022","unstructured":"Yuta Saito and Thorsten Joachims. 2022. Off-Policy Evaluation for Large Action Spaces via Embeddings. In International Conference on Machine Learning. PMLR, PMLR, Baltimore, Maryland, USA, 19089\u201319122."},{"key":"e_1_3_2_2_22_1","volume-title":"Hyperparameter Optimization Can Even be Harmful in Off-Policy Learning and How to Deal with It. arXiv preprint arXiv:2404.15084","author":"Saito Yuta","year":"2024","unstructured":"Yuta Saito and Masahiro Nomura. 2024. Hyperparameter Optimization Can Even be Harmful in Off-Policy Learning and How to Deal with It. arXiv preprint arXiv:2404.15084 (2024)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/3618408.3619642"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474245"},{"key":"e_1_3_2_2_25_1","volume-title":"POTEC: Off-Policy Learning for Large Action Spaces via Two-Stage Policy Decomposition. arXiv preprint arXiv:2402.06151","author":"Saito Yuta","year":"2024","unstructured":"Yuta Saito, Jihan Yao, and Thorsten Joachims. 2024. POTEC: Off-Policy Learning for Large Action Spaces via Two-Stage Policy Decomposition. arXiv preprint arXiv:2402.06151 (2024)."},{"key":"e_1_3_2_2_26_1","volume-title":"Advances in Neural Information Processing Systems, Vol.\u00a023","author":"Strehl Alex","unstructured":"Alex Strehl, John Langford, Lihong Li, and Sham\u00a0M Kakade. 2010. Learning from Logged Implicit Exploration Data. In Advances in Neural Information Processing Systems, Vol.\u00a023. Curran Associates Inc., Vancouver British Columbia, Canada, 2217\u20132225."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525788"},{"key":"e_1_3_2_2_28_1","volume-title":"International Conference on Machine Learning. PMLR, PMLR, Online, 9196\u20139205","author":"Su Yi","year":"2020","unstructured":"Yi Su, Pavithra Srinath, and Akshay Krishnamurthy. 2020. Adaptive estimator selection for off-policy evaluation. In International Conference on Machine Learning. PMLR, PMLR, Online, 9196\u20139205."},{"key":"e_1_3_2_2_29_1","volume-title":"International Conference on Machine Learning, Vol.\u00a084","author":"Su Yi","year":"2019","unstructured":"Yi Su, Lequn Wang, Michele Santacatterina, and Thorsten Joachims. 2019. Cab: Continuous adaptive blending for policy evaluation and learning. In International Conference on Machine Learning, Vol.\u00a084. PMLR, Long Beach, California, USA, 6005\u20136014."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/2789272.2886805"},{"key":"e_1_3_2_2_31_1","volume-title":"International Conference on Machine Learning. PMLR, PMLR","author":"Swaminathan Adith","year":"2015","unstructured":"Adith Swaminathan and Thorsten Joachims. 2015. Counterfactual risk minimization: Learning from logged bandit feedback. In International Conference on Machine Learning. PMLR, PMLR, Lille, France, 814\u2013823."},{"key":"e_1_3_2_2_32_1","volume-title":"Advances in Neural Information Processing Systems, Vol.\u00a030","author":"Swaminathan Adith","unstructured":"Adith Swaminathan, Akshay Krishnamurthy, Alekh Agarwal, Miro Dudik, John Langford, Damien Jose, and Imed Zitouni. 2017. Off-Policy Evaluation for Slate Recommendation. In Advances in Neural Information Processing Systems, Vol.\u00a030. Curran Associates Inc., Long Beach, CA, USA, 3632\u20133642."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26195"},{"key":"e_1_3_2_2_34_1","first-page":"3667","article-title":"Control variates for slate off-policy evaluation","volume":"34","author":"Vlassis Nikos","year":"2021","unstructured":"Nikos Vlassis, Ashok Chandrashekar, Fernando Amat, and Nathan Kallus. 2021. Control variates for slate off-policy evaluation. Advances in Neural Information Processing Systems 34 (2021), 3667\u20133679.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_35_1","volume-title":"International Conference on Machine Learning. PMLR, PMLR","author":"Wang Yu-Xiang","year":"2017","unstructured":"Yu-Xiang Wang, Alekh Agarwal, and Miroslav Dud\u0131k. 2017. Optimal and adaptive off-policy evaluation in contextual bandits. In International Conference on Machine Learning. PMLR, PMLR, Sydney, Australia, 3589\u20133597."}],"event":{"name":"RecSys '24: 18th ACM Conference on Recommender Systems","location":"Bari Italy","acronym":"RecSys '24","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"]},"container-title":["18th ACM Conference on Recommender Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640457.3688099","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3640457.3688099","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:29Z","timestamp":1750294709000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640457.3688099"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,8]]},"references-count":35,"alternative-id":["10.1145\/3640457.3688099","10.1145\/3640457"],"URL":"https:\/\/doi.org\/10.1145\/3640457.3688099","relation":{},"subject":[],"published":{"date-parts":[[2024,10,8]]},"assertion":[{"value":"2024-10-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}