{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:10:15Z","timestamp":1757617815189,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,22]]},"DOI":"10.1145\/3705328.3748011","type":"proceedings-article","created":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T10:51:29Z","timestamp":1757155889000},"page":"551-557","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Counterfactual Inference under Thompson Sampling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6256-5814","authenticated-orcid":false,"given":"Olivier","family":"Jeunen","sequence":"first","affiliation":[{"name":"Aampe, Antwerp, Belgium"}]}],"member":"320","published-online":{"date-parts":[[2025,9,7]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_3_2_2_2","DOI":"10.1145\/3240323.3241729"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_3_2","DOI":"10.1145\/3383313.3412217"},{"unstructured":"L\u00e9on Bottou Jonas Peters Joaquin Qui\u00f1onero-Candela Denis\u00a0X. Charles D.\u00a0Max Chickering Elon Portugaly Dipankar Ray Patrice Simard and Ed Snelson. 2013. Counterfactual Reasoning and Learning Systems: The Example of Computational Advertising. Journal of Machine Learning Research 14 101 (2013) 3207\u20133260. http:\/\/jmlr.org\/papers\/v14\/bottou13a.html","key":"e_1_3_3_2_4_2"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_5_2","DOI":"10.1145\/3172944.3172967"},{"key":"e_1_3_3_2_6_2","first-page":"27475","volume-title":"Advances in Neural Information Processing Systems","author":"Chandak Yash","year":"2021","unstructured":"Yash Chandak, Scott Niekum, Bruno da Silva, Erik Learned-Miller, Emma Brunskill, and Philip\u00a0S. Thomas. 2021. Universal Off-Policy Evaluation. In Advances in Neural Information Processing Systems , Vol.\u00a034. Curran Associates, Inc., 27475\u201327490. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/e71e5cd119bbc5797164fb0cd7fd94a4-Paper.pdf"},{"key":"e_1_3_3_2_7_2","volume-title":"Advances in Neural Information Processing Systems","author":"Chapelle Olivier","year":"2011","unstructured":"Olivier Chapelle and Lihong Li. 2011. An Empirical Evaluation of Thompson Sampling. In Advances in Neural Information Processing Systems , Vol.\u00a024. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper\/2011\/file\/e53a0a2978c28872a4505bdb51db06dc-Paper.pdf"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_8_2","DOI":"10.1145\/3289600.3290999"},{"doi-asserted-by":"crossref","unstructured":"Miroslav Dud\u00edk Dumitru Erhan John Langford and Lihong Li. 2014. Doubly Robust Policy Evaluation and Optimization. Statist. Sci. 29 4 (2014) 485\u2013511. http:\/\/www.jstor.org\/stable\/43288496","key":"e_1_3_3_2_9_2","DOI":"10.1214\/14-STS500"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_10_2","DOI":"10.1017\/9781108591034"},{"doi-asserted-by":"publisher","unstructured":"Simen Eide David\u00a0S. Leslie and Arnoldo Frigessi. 2022. Dynamic slate recommendation with gated recurrent units and Thompson sampling. Data Mining and Knowledge Discovery 36 5 (01 Sep 2022) 1756\u20131786. 10.1007\/s10618-022-00849-w","key":"e_1_3_3_2_11_2","DOI":"10.1007\/s10618-022-00849-w"},{"key":"e_1_3_3_2_12_2","series-title":"ICML\u201918","first-page":"1447","volume-title":"Proc. of the 35th International Conference on Machine Learning","volume":"80","author":"Farajtabar Mehrdad","year":"2018","unstructured":"Mehrdad Farajtabar, Yinlam Chow, and Mohammad Ghavamzadeh. 2018. More Robust Doubly Robust Off-policy Evaluation. In Proc. of the 35th International Conference on Machine Learning(ICML\u201918, Vol.\u00a080). PMLR, 1447\u20131456."},{"doi-asserted-by":"publisher","unstructured":"Chen Gao Yu Zheng Wenjie Wang Fuli Feng Xiangnan He and Yong Li. 2024. Causal Inference in Recommender Systems: A Survey and Future Directions. ACM Trans. Inf. Syst. 42 4 Article 88 (Feb. 2024) 32\u00a0pages. 10.1145\/3639048","key":"e_1_3_3_2_13_2","DOI":"10.1145\/3639048"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_14_2","DOI":"10.1145\/3159652.3159687"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_15_2","DOI":"10.1145\/3289600.3291027"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_16_2","DOI":"10.1145\/3616855.3636451"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_17_2","DOI":"10.1145\/3640457.3688105"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_18_2","DOI":"10.1145\/3627673.3679531"},{"unstructured":"Marcelo Hartmann. 2017. Extending Owen\u2019s integral table and a new multivariate Bernoulli distribution. arxiv:https:\/\/arXiv.org\/abs\/1704.04736\u00a0[stat.ME] https:\/\/arxiv.org\/abs\/1704.04736","key":"e_1_3_3_2_19_2"},{"doi-asserted-by":"crossref","unstructured":"Edward\u00a0L. Ionides. 2008. Truncated Importance Sampling. Journal of Computational and Graphical Statistics 17 2 (2008) 295\u2013311.","key":"e_1_3_3_2_20_2","DOI":"10.1198\/106186008X320456"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_21_2","DOI":"10.1145\/3298689.3347069"},{"unstructured":"Olivier Jeunen. 2021. Offline Approaches to Recommendation with Online Success. Ph.\u00a0D. Dissertation. University of Antwerp.","key":"e_1_3_3_2_22_2"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_23_2","DOI":"10.1145\/3604915.3608777"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_24_2","DOI":"10.1145\/3460231.3474247"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_25_2","DOI":"10.1145\/3460231.3474248"},{"doi-asserted-by":"publisher","unstructured":"Olivier Jeunen and Bart Goethals. 2023. Pessimistic Decision-Making for Recommender Systems. ACM Trans. Recomm. Syst. 1 1 Article 4 (feb 2023) 27\u00a0pages. 10.1145\/3568029","key":"e_1_3_3_2_26_2","DOI":"10.1145\/3568029"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_27_2","DOI":"10.1145\/3523227.3547409"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_28_2","DOI":"10.1145\/3640457.3688132"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_29_2","DOI":"10.1145\/3580305.3599877"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_30_2","DOI":"10.1145\/3637528.3671687"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_31_2","DOI":"10.1145\/3394486.3403175"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_32_2","DOI":"10.1145\/3640457.3688162"},{"key":"e_1_3_3_2_33_2","series-title":"Proc. of Machine Learning Research","first-page":"15239","volume-title":"Proc. of the 40th International Conference on Machine Learning","volume":"202","author":"Jin Tianyuan","year":"2023","unstructured":"Tianyuan Jin, Xianglin Yang, Xiaokui Xiao, and Pan Xu. 2023. Thompson Sampling with Less Exploration is Fast and Optimal. In Proc. of the 40th International Conference on Machine Learning(Proc. of Machine Learning Research, Vol.\u00a0202). PMLR, 15239\u201315261. https:\/\/proceedings.mlr.press\/v202\/jin23b.html"},{"doi-asserted-by":"publisher","unstructured":"Thorsten Joachims Ben London Yi Su Adith Swaminathan and Lequn Wang. 2021. Recommendations as Treatments. AI Magazine 42 3 (Nov. 2021) 19\u201330. 10.1609\/aimag.v42i3.18141","key":"e_1_3_3_2_34_2","DOI":"10.1609\/aimag.v42i3.18141"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_35_2","DOI":"10.1145\/3018661.3018699"},{"key":"e_1_3_3_2_36_2","series-title":"ICML \u201912","first-page":"592","volume-title":"Proc. of the Fifteenth International Conference on Artificial Intelligence and Statistics","volume":"22","author":"Kaufmann Emilie","year":"2012","unstructured":"Emilie Kaufmann, Olivier Cappe, and Aurelien Garivier. 2012. On Bayesian Upper Confidence Bounds for Bandit Problems. In Proc. of the Fifteenth International Conference on Artificial Intelligence and Statistics(ICML \u201912, Vol.\u00a022). PMLR, 592\u2013600. https:\/\/proceedings.mlr.press\/v22\/kaufmann12.html"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_37_2","DOI":"10.1017\/9781108571401"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_38_2","DOI":"10.1145\/1935826.1935878"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_39_2","DOI":"10.1145\/3240323.3240408"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_40_2","DOI":"10.1145\/3366423.3380130"},{"unstructured":"Evan Miller. 2015. Formulas for Bayesian A\/B testing. https:\/\/www.evanmiller.org\/bayesian-ab-testing.html","key":"e_1_3_3_2_41_2"},{"key":"e_1_3_3_2_42_2","volume-title":"Probabilistic Machine Learning: An introduction","author":"Murphy Kevin\u00a0P.","year":"2022","unstructured":"Kevin\u00a0P. Murphy. 2022. Probabilistic Machine Learning: An introduction. MIT Press. http:\/\/probml.github.io\/book1"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_43_2","DOI":"10.1145\/3397271.3401102"},{"key":"e_1_3_3_2_44_2","volume-title":"Monte Carlo theory, methods and examples","author":"Owen Art\u00a0B.","year":"2013","unstructured":"Art\u00a0B. Owen. 2013. Monte Carlo theory, methods and examples."},{"doi-asserted-by":"crossref","unstructured":"Herbert Robbins. 1952. Some aspects of the sequential design of experiments. Bull. Amer. Math. Soc. 58 (1952) 527\u2013535.","key":"e_1_3_3_2_45_2","DOI":"10.1090\/S0002-9904-1952-09620-8"},{"doi-asserted-by":"publisher","unstructured":"Daniel\u00a0J. Russo Benjamin\u00a0Van Roy Abbas Kazerouni Ian Osband and Zheng Wen. 2018. A Tutorial on Thompson Sampling. Foundations and Trends\u00ae in Machine Learning 11 1 (2018) 1\u201396. 10.1561\/2200000070","key":"e_1_3_3_2_46_2","DOI":"10.1561\/2200000070"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_47_2","DOI":"10.1145\/3616855.3635846"},{"key":"e_1_3_3_2_48_2","volume-title":"Proc. of the Neural Information Processing Systems Track on Datasets and Benchmarks","author":"Saito Yuta","year":"2021","unstructured":"Yuta Saito, Shunsuke Aihara, Megumi Matsutani, and Yusuke Narita. 2021. Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluation. In Proc. of the Neural Information Processing Systems Track on Datasets and Benchmarks , Vol.\u00a01. https:\/\/datasets-benchmarks-proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/33e75ff09dd601bbe69f351039152189-Paper-round2.pdf"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_49_2","DOI":"10.1145\/3460231.3473320"},{"key":"e_1_3_3_2_50_2","series-title":"Proc. of Machine Learning Research","first-page":"19089","volume-title":"Proc. of the 39th International Conference on Machine Learning","volume":"162","author":"Saito Yuta","year":"2022","unstructured":"Yuta Saito and Thorsten Joachims. 2022. Off-Policy Evaluation for Large Action Spaces via Embeddings. In Proc. of the 39th International Conference on Machine Learning(Proc. of Machine Learning Research, Vol.\u00a0162). PMLR, 19089\u201319122. https:\/\/proceedings.mlr.press\/v162\/saito22a.html"},{"key":"e_1_3_3_2_51_2","series-title":"Proc. of Machine Learning Research","first-page":"29734","volume-title":"Proc. of the 40th International Conference on Machine Learning","volume":"202","author":"Saito Yuta","year":"2023","unstructured":"Yuta Saito, Qingyang Ren, and Thorsten Joachims. 2023. Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling. In Proc. of the 40th International Conference on Machine Learning(Proc. of Machine Learning Research, Vol.\u00a0202). PMLR, 29734\u201329759. https:\/\/proceedings.mlr.press\/v202\/saito23b.html"},{"key":"e_1_3_3_2_52_2","series-title":"Proceedings of Machine Learning Research","first-page":"29777","volume-title":"Proc. of the 40th International Conference on Machine Learning","volume":"202","author":"Sakhi Otmane","year":"2023","unstructured":"Otmane Sakhi, Pierre Alquier, and Nicolas Chopin. 2023. PAC-Bayesian Offline Contextual Bandits With Guarantees. In Proc. of the 40th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0202), Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett (Eds.). PMLR, 29777\u201329799. https:\/\/proceedings.mlr.press\/v202\/sakhi23a.html"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_53_2","DOI":"10.1145\/3604915.3610245"},{"key":"e_1_3_3_2_54_2","series-title":"Proc. of Machine Learning Research","first-page":"9167","volume-title":"Proc. of the 37th International Conference on Machine Learning","volume":"119","author":"Su Yi","year":"2020","unstructured":"Yi Su, Maria Dimakopoulou, Akshay Krishnamurthy, and Miroslav Dudik. 2020. Doubly robust off-policy evaluation with shrinkage. In Proc. of the 37th International Conference on Machine Learning(Proc. of Machine Learning Research, Vol.\u00a0119). PMLR, 9167\u20139176. https:\/\/proceedings.mlr.press\/v119\/su20a.html"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_55_2","DOI":"10.1145\/3637528.3671649"},{"key":"e_1_3_3_2_56_2","volume-title":"Advances in Neural Information Processing Systems","author":"Swaminathan Adith","year":"2015","unstructured":"Adith Swaminathan and Thorsten Joachims. 2015. The Self-Normalized Estimator for Counterfactual Learning. In Advances in Neural Information Processing Systems , Vol.\u00a028. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2015\/file\/39027dfad5138c9ca0c474d71db915c3-Paper.pdf"},{"doi-asserted-by":"crossref","unstructured":"William\u00a0R. Thompson. 1933. On the Likelihood that One Unknown Probability Exceeds Another in View of the Evidence of Two Samples. Biometrika 25 3\/4 (1933) 285\u2013294. http:\/\/www.jstor.org\/stable\/2332286","key":"e_1_3_3_2_57_2","DOI":"10.1093\/biomet\/25.3-4.285"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_58_2","DOI":"10.1145\/3616855.3636449"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_59_2","DOI":"10.1145\/3340631.3398666"},{"doi-asserted-by":"publisher","unstructured":"Pauli Virtanen\u00a0et al.2020. SciPy 1.0: fundamental algorithms for scientific computing in Python. Nature Methods 17 3 (01 Mar 2020) 261\u2013272. 10.1038\/s41592-019-0686-2","key":"e_1_3_3_2_60_2","DOI":"10.1038\/s41592-019-0686-2"},{"key":"e_1_3_3_2_61_2","series-title":"ICML\u201919","first-page":"6468","volume-title":"Proc. of the 36th International Conference on Machine Learning","volume":"97","author":"Vlassis Nikos","year":"2019","unstructured":"Nikos Vlassis, Aurelien Bibaut, Maria Dimakopoulou, and Tony Jebara. 2019. On the Design of Estimators for Bandit Off-Policy Evaluation. In Proc. of the 36th International Conference on Machine Learning(ICML\u201919, Vol.\u00a097). PMLR, 6468\u20136476."},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_62_2","DOI":"10.1145\/3383313.3412225"},{"key":"e_1_3_3_2_63_2","series-title":"Proc. of Machine Learning Research","first-page":"1198","volume-title":"Proc. of The 24th International Conference on Artificial Intelligence and Statistics","volume":"130","author":"Watson Joe","year":"2021","unstructured":"Joe Watson, Jihao Andreas\u00a0Lin, Pascal Klink, Joni Pajarinen, and Jan Peters. 2021. Latent Derivative Bayesian Last Layer Networks. In Proc. of The 24th International Conference on Artificial Intelligence and Statistics(Proc. of Machine Learning Research, Vol.\u00a0130). PMLR, 1198\u20131206. https:\/\/proceedings.mlr.press\/v130\/watson21a.html"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_64_2","DOI":"10.1145\/3240323.3240355"},{"key":"e_1_3_3_2_65_2","volume-title":"Advances in Neural Information Processing Systems","author":"Zhang Liangpeng","year":"2017","unstructured":"Liangpeng Zhang, Ke Tang, and Xin Yao. 2017. Log-normality and Skewness of Estimated State\/Action Values in Reinforcement Learning. In Advances in Neural Information Processing Systems , I.\u00a0Guyon, U.\u00a0Von Luxburg, S.\u00a0Bengio, H.\u00a0Wallach, R.\u00a0Fergus, S.\u00a0Vishwanathan, and R.\u00a0Garnett (Eds.), Vol.\u00a030. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/69a5b5995110b36a9a347898d97a610e-Paper.pdf"},{"key":"e_1_3_3_2_66_2","series-title":"(ICLR \u201921)","volume-title":"International Conference on Learning Representations","author":"Zhang Weitong","year":"2021","unstructured":"Weitong Zhang, Dongruo Zhou, Lihong Li, and Quanquan Gu. 2021. Neural Thompson Sampling. In International Conference on Learning Representations(ICLR \u201921). https:\/\/openreview.net\/forum?id=tkAtoZkcUnm"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_67_2","DOI":"10.1145\/3604915.3608855"}],"event":{"sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGAI ACM Special Interest Group on Artificial Intelligence","SIGIR ACM Special Interest Group on Information Retrieval","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"acronym":"RecSys '25","name":"RecSys '25: Nineteenth ACM Conference on Recommender Systems","location":"Prague Czech Republic"},"container-title":["Proceedings of the Nineteenth ACM Conference on Recommender Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3705328.3748011","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T11:46:53Z","timestamp":1757159213000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3705328.3748011"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,7]]},"references-count":66,"alternative-id":["10.1145\/3705328.3748011","10.1145\/3705328"],"URL":"https:\/\/doi.org\/10.1145\/3705328.3748011","relation":{},"subject":[],"published":{"date-parts":[[2025,9,7]]},"assertion":[{"value":"2025-09-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}