{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T13:59:40Z","timestamp":1753883980949,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,8,14]],"date-time":"2021-08-14T00:00:00Z","timestamp":1628899200000},"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":[[2021,8,14]]},"DOI":"10.1145\/3447548.3467089","type":"proceedings-article","created":{"date-parts":[[2021,8,12]],"date-time":"2021-08-12T06:12:05Z","timestamp":1628748725000},"page":"2792-2801","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Exploration in Online Advertising Systems with Deep Uncertainty-Aware Learning"],"prefix":"10.1145","author":[{"given":"Chao","family":"Du","sequence":"first","affiliation":[{"name":"Alibaba Group, Beijing, China"}]},{"given":"Zhifeng","family":"Gao","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}]},{"given":"Shuo","family":"Yuan","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}]},{"given":"Lining","family":"Gao","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}]},{"given":"Ziyan","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}]},{"given":"Yifan","family":"Zeng","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}]},{"given":"Xiaoqiang","family":"Zhu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}]},{"given":"Jian","family":"Xu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}]},{"given":"Kun","family":"Gai","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}]},{"given":"Kuang-Chih","family":"Lee","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2021,8,14]]},"reference":[{"key":"e_1_3_2_2_1_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 , Vol. 3 , Nov (2002), 397 -- 422 . Peter Auer. 2002. Using confidence bounds for exploitation-exploration trade-offs. Journal of Machine Learning Research, Vol. 3, Nov (2002), 397--422.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008205606173"},{"key":"e_1_3_2_2_3_1","volume-title":"Weight uncertainty in neural networks. arXiv preprint arXiv:1505.05424","author":"Blundell Charles","year":"2015","unstructured":"Charles Blundell , Julien Cornebise , Koray Kavukcuoglu , and Daan Wierstra . 2015. Weight uncertainty in neural networks. arXiv preprint arXiv:1505.05424 ( 2015 ). Charles Blundell, Julien Cornebise, Koray Kavukcuoglu, and Daan Wierstra. 2015. Weight uncertainty in neural networks. arXiv preprint arXiv:1505.05424 (2015)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1454008.1454009"},{"key":"e_1_3_2_2_6_1","first-page":"1023","article-title":"The racist algorithm","volume":"115","author":"Chander Anupam","year":"2016","unstructured":"Anupam Chander . 2016 . The racist algorithm . Mich. L. Rev. , Vol. 115 (2016), 1023 . Anupam Chander. 2016. The racist algorithm. Mich. L. Rev., Vol. 115 (2016), 1023.","journal-title":"Mich. L. Rev."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240370"},{"key":"e_1_3_2_2_8_1","unstructured":"Olivier Chapelle and Lihong Li. 2011. An empirical evaluation of thompson sampling. In Advances in neural information processing systems. 2249--2257.  Olivier Chapelle and Lihong Li. 2011. An empirical evaluation of thompson sampling. In Advances in neural information processing systems. 2249--2257."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_2_10_1","volume-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics. 208--214","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--214 . 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--214."},{"key":"e_1_3_2_2_11_1","unstructured":"Bianca Dumitrascu Karen Feng and Barbara Engelhardt. 2018. PG-TS: Improved Thompson sampling for logistic contextual bandits. In Advances in neural information processing systems. 4624--4633.  Bianca Dumitrascu Karen Feng and Barbara Engelhardt. 2018. PG-TS: Improved Thompson sampling for logistic contextual bandits. In Advances in neural information processing systems. 4624--4633."},{"key":"e_1_3_2_2_12_1","volume-title":"Internet advertising and the generalized second-price auction: Selling billions of dollars worth of keywords. American economic review","author":"Edelman Benjamin","year":"2007","unstructured":"Benjamin Edelman , Michael Ostrovsky , and Michael Schwarz . 2007. Internet advertising and the generalized second-price auction: Selling billions of dollars worth of keywords. American economic review , Vol. 97 , 1 ( 2007 ), 242--259. Benjamin Edelman, Michael Ostrovsky, and Michael Schwarz. 2007. Internet advertising and the generalized second-price auction: Selling billions of dollars worth of keywords. American economic review, Vol. 97, 1 (2007), 242--259."},{"key":"e_1_3_2_2_13_1","volume-title":"Deep session interest network for click-through rate prediction. arXiv preprint arXiv:1905.06482","author":"Feng Yufei","year":"2019","unstructured":"Yufei Feng , Fuyu Lv , Weichen Shen , Menghan Wang , Fei Sun , Yu Zhu , and Keping Yang . 2019. Deep session interest network for click-through rate prediction. arXiv preprint arXiv:1905.06482 ( 2019 ). Yufei Feng, Fuyu Lv, Weichen Shen, Menghan Wang, Fei Sun, Yu Zhu, and Keping Yang. 2019. Deep session interest network for click-through rate prediction. arXiv preprint arXiv:1905.06482 (2019)."},{"key":"e_1_3_2_2_14_1","unstructured":"Sarah Filippi Olivier Cappe Aur\u00e9lien Garivier and Csaba Szepesv\u00e1ri. 2010. Parametric bandits: The generalized linear case. In Advances in Neural Information Processing Systems. 586--594.  Sarah Filippi Olivier Cappe Aur\u00e9lien Garivier and Csaba Szepesv\u00e1ri. 2010. Parametric bandits: The generalized linear case. In Advances in Neural Information Processing Systems. 586--594."},{"key":"e_1_3_2_2_15_1","volume-title":"international conference on machine learning. 1050--1059","author":"Gal Yarin","year":"2016","unstructured":"Yarin Gal and Zoubin Ghahramani . 2016 . Dropout as a bayesian approximation: Representing model uncertainty in deep learning . In international conference on machine learning. 1050--1059 . Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In international conference on machine learning. 1050--1059."},{"key":"e_1_3_2_2_16_1","unstructured":"Alex Graves. 2011. Practical variational inference for neural networks. In Advances in neural information processing systems. 2348--2356.  Alex Graves. 2011. Practical variational inference for neural networks. In Advances in neural information processing systems. 2348--2356."},{"key":"e_1_3_2_2_17_1","volume-title":"Ferenc Huszar, Pranay Kumar Myana, Wenzhe Shi, and Alykhan Tejani.","author":"Guo Dalin","year":"2020","unstructured":"Dalin Guo , Sofia Ira Ktena , Ferenc Huszar, Pranay Kumar Myana, Wenzhe Shi, and Alykhan Tejani. 2020 . Deep Bayesian Bandits: Exploring in Online Personalized Recommendations . arxiv: 2008.00727 [cs.LG] Dalin Guo, Sofia Ira Ktena, Ferenc Huszar, Pranay Kumar Myana, Wenzhe Shi, and Alykhan Tejani. 2020. Deep Bayesian Bandits: Exploring in Online Personalized Recommendations. arxiv: 2008.00727 [cs.LG]"},{"key":"e_1_3_2_2_18_1","unstructured":"Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: a factorization-machine based neural network for CTR prediction. arXiv preprint arXiv:1703.04247 (2017).  Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: a factorization-machine based neural network for CTR prediction. arXiv preprint arXiv:1703.04247 (2017)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_2_2_20_1","volume-title":"Gaussian processes for big data. arXiv preprint arXiv:1309.6835","author":"Hensman James","year":"2013","unstructured":"James Hensman , Nicolo Fusi , and Neil D Lawrence . 2013. Gaussian processes for big data. arXiv preprint arXiv:1309.6835 ( 2013 ). James Hensman, Nicolo Fusi, and Neil D Lawrence. 2013. Gaussian processes for big data. arXiv preprint arXiv:1309.6835 (2013)."},{"key":"e_1_3_2_2_21_1","unstructured":"James Hensman Alexander Matthews and Zoubin Ghahramani. 2015. Scalable variational Gaussian process classification. (2015).  James Hensman Alexander Matthews and Zoubin Ghahramani. 2015. Scalable variational Gaussian process classification. (2015)."},{"key":"e_1_3_2_2_22_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_23_1","unstructured":"Andreas Krause and Cheng S Ong. 2011. Contextual gaussian process bandit optimization. In Advances in neural information processing systems. 2447--2455.  Andreas Krause and Cheng S Ong. 2011. Contextual gaussian process bandit optimization. In Advances in neural information processing systems. 2447--2455."},{"key":"e_1_3_2_2_24_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--6413.  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--6413."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1935826.1935878"},{"key":"e_1_3_2_2_27_1","volume-title":"Provably optimal algorithms for generalized linear contextual bandits. arXiv preprint arXiv:1703.00048","author":"Li Lihong","year":"2017","unstructured":"Lihong Li , Yu Lu , and Dengyong Zhou . 2017. Provably optimal algorithms for generalized linear contextual bandits. arXiv preprint arXiv:1703.00048 ( 2017 ). Lihong Li, Yu Lu, and Dengyong Zhou. 2017. Provably optimal algorithms for generalized linear contextual bandits. arXiv preprint arXiv:1703.00048 (2017)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2012.09.019"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240354"},{"volume-title":"Machine learning: a probabilistic perspective","author":"Murphy Kevin P","key":"e_1_3_2_2_31_1","unstructured":"Kevin P Murphy . 2012. Machine learning: a probabilistic perspective . MIT press . Kevin P Murphy. 2012. Machine learning: a probabilistic perspective .MIT press."},{"key":"e_1_3_2_2_32_1","volume-title":"Optimal auction design. Mathematics of operations research","author":"Myerson Roger B","year":"1981","unstructured":"Roger B Myerson . 1981. Optimal auction design. Mathematics of operations research , Vol. 6 , 1 ( 1981 ), 58--73. Roger B Myerson. 1981. Optimal auction design. Mathematics of operations research, Vol. 6, 1 (1981), 58--73."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0151"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390255"},{"volume-title":"Gaussian Processes for Machine Learning","author":"Rasmussen CE.","key":"e_1_3_2_2_35_1","unstructured":"CE. Rasmussen and CKI. Williams . 2006. Gaussian Processes for Machine Learning . MIT Press , Cambridge, MA, USA . 248 pages. CE. Rasmussen and CKI. Williams. 2006. Gaussian Processes for Machine Learning .MIT Press, Cambridge, MA, USA. 248 pages."},{"key":"e_1_3_2_2_36_1","unstructured":"Hugh Salimbeni and Marc Deisenroth. 2017. Doubly stochastic variational inference for deep Gaussian processes. In Advances in Neural Information Processing Systems. 4588--4599.  Hugh Salimbeni and Marc Deisenroth. 2017. Doubly stochastic variational inference for deep Gaussian processes. In Advances in Neural Information Processing Systems. 4588--4599."},{"key":"e_1_3_2_2_37_1","volume-title":"International Conference on Artificial Intelligence and Statistics. 1932--1942","author":"Shi Jiaxin","year":"2020","unstructured":"Jiaxin Shi , Michalis Titsias , and Andriy Mnih . 2020 . Sparse orthogonal variational inference for gaussian processes . In International Conference on Artificial Intelligence and Statistics. 1932--1942 . Jiaxin Shi, Michalis Titsias, and Andriy Mnih. 2020. Sparse orthogonal variational inference for gaussian processes. In International Conference on Artificial Intelligence and Statistics. 1932--1942."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2011.2182033"},{"key":"e_1_3_2_2_39_1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton R.S.","year":"2018","unstructured":"R.S. Sutton and A.G. Barto . 2018 . Reinforcement Learning: An Introduction . MIT Press . 2018023826 R.S. Sutton and A.G. Barto. 2018. Reinforcement Learning: An Introduction .MIT Press. 2018023826"},{"key":"e_1_3_2_2_40_1","unstructured":"Michalis Titsias. 2009. Variational learning of inducing variables in sparse Gaussian processes. In Artificial Intelligence and Statistics. 567--574.  Michalis Titsias. 2009. Variational learning of inducing variables in sparse Gaussian processes. In Artificial Intelligence and Statistics. 567--574."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2645710.2645733"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3264-1"},{"key":"e_1_3_2_2_43_1","volume-title":"Proceedings of the 28th international conference on machine learning (ICML-11)","author":"Welling Max","year":"2011","unstructured":"Max Welling and Yee W Teh . 2011 . Bayesian learning via stochastic gradient Langevin dynamics . In Proceedings of the 28th international conference on machine learning (ICML-11) . 681--688. Max Welling and Yee W Teh. 2011. Bayesian learning via stochastic gradient Langevin dynamics. In Proceedings of the 28th international conference on machine learning (ICML-11). 681--688."},{"key":"e_1_3_2_2_44_1","volume-title":"Linh Tran, Stephan Mandt, Jasper Snoek, Tim Salimans, Rodolphe Jenatton, and Sebastian Nowozin.","author":"Wenzel Florian","year":"2020","unstructured":"Florian Wenzel , Kevin Roth , Bastiaan S Veeling , Jakub 'Swika tkowski , Linh Tran, Stephan Mandt, Jasper Snoek, Tim Salimans, Rodolphe Jenatton, and Sebastian Nowozin. 2020 . How good is the bayes posterior in deep neural networks really? arXiv preprint arXiv:2002.02405 (2020). Florian Wenzel, Kevin Roth, Bastiaan S Veeling, Jakub 'Swika tkowski, Linh Tran, Stephan Mandt, Jasper Snoek, Tim Salimans, Rodolphe Jenatton, and Sebastian Nowozin. 2020. How good is the bayes posterior in deep neural networks really? arXiv preprint arXiv:2002.02405 (2020)."},{"key":"e_1_3_2_2_45_1","unstructured":"Andrew Gordon Wilson Zhiting Hu Ruslan Salakhutdinov and Eric P Xing. 2016a. Deep kernel learning. In Artificial intelligence and statistics. 370--378.  Andrew Gordon Wilson Zhiting Hu Ruslan Salakhutdinov and Eric P Xing. 2016a. Deep kernel learning. In Artificial intelligence and statistics. 370--378."},{"key":"e_1_3_2_2_46_1","unstructured":"Andrew G Wilson Zhiting Hu Russ R Salakhutdinov and Eric P Xing. 2016b. Stochastic variational deep kernel learning. In Advances in Neural Information Processing Systems. 2586--2594.  Andrew G Wilson Zhiting Hu Russ R Salakhutdinov and Eric P Xing. 2016b. Stochastic variational deep kernel learning. In Advances in Neural Information Processing Systems. 2586--2594."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271748"},{"key":"e_1_3_2_2_48_1","unstructured":"Yahoo! [n.d.]. Yahoo! webscope program. https:\/\/webscope.sandbox.yahoo.com\/. Accessed: 2020--10--19.  Yahoo! [n.d.]. Yahoo! webscope program. https:\/\/webscope.sandbox.yahoo.com\/. Accessed: 2020--10--19."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219918"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015941"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098134"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219826"},{"key":"e_1_3_2_2_54_1","volume-title":"Learning Optimal Tree Models under Beam Search. arXiv preprint arXiv:2006.15408","author":"Zhuo Jingwei","year":"2020","unstructured":"Jingwei Zhuo , Ziru Xu , Wei Dai , Han Zhu , Han Li , Jian Xu , and Kun Gai . 2020. Learning Optimal Tree Models under Beam Search. arXiv preprint arXiv:2006.15408 ( 2020 ). Jingwei Zhuo, Ziru Xu, Wei Dai, Han Zhu, Han Li, Jian Xu, and Kun Gai. 2020. Learning Optimal Tree Models under Beam Search. arXiv preprint arXiv:2006.15408 (2020)."}],"event":{"name":"KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Virtual Event Singapore","acronym":"KDD '21"},"container-title":["Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3447548.3467089","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3447548.3467089","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:28:04Z","timestamp":1750195684000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3447548.3467089"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,14]]},"references-count":54,"alternative-id":["10.1145\/3447548.3467089","10.1145\/3447548"],"URL":"https:\/\/doi.org\/10.1145\/3447548.3467089","relation":{},"subject":[],"published":{"date-parts":[[2021,8,14]]},"assertion":[{"value":"2021-08-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}