{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:24:17Z","timestamp":1776885857054,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["ECCS-2127721"],"award-info":[{"award-number":["ECCS-2127721"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CCF-2332800"],"award-info":[{"award-number":["CCF-2332800"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"U.S. Army Research Office","award":["W911NF-22-1-0151"],"award-info":[{"award-number":["W911NF-22-1-0151"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1145\/3641512.3686369","type":"proceedings-article","created":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T21:11:22Z","timestamp":1727817082000},"page":"41-50","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Distributed No-Regret Learning for Multi-Stage Systems with End-to-End Bandit Feedback"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1166-8773","authenticated-orcid":false,"given":"I-Hong","family":"Hou","sequence":"first","affiliation":[{"name":"ECE, Texas A&M University, College Station, Texas, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/3586589.3586801"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOTS.2012.14"},{"key":"e_1_3_2_1_3_1","first-page":"1","article-title":"Minimax Policies for Adversarial and Stochastic Bandits","volume":"7","author":"Audibert Jean-Yves","year":"2009","unstructured":"Jean-Yves Audibert and S\u00e9bastien Bubeck. 2009. Minimax Policies for Adversarial and Stochastic Bandits.. In COLT, Vol. 7. 1--122.","journal-title":"COLT"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/1756006.1953023"},{"key":"e_1_3_2_1_5_1","series-title":"SIAM journal on computing 32, 1","volume-title":"The nonstochastic multiarmed bandit problem","author":"Auer Peter","year":"2002","unstructured":"Peter Auer, Nicolo Cesa-Bianchi, Yoav Freund, and Robert E Schapire. 2002. The nonstochastic multiarmed bandit problem. SIAM journal on computing 32, 1 (2002), 48--77."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2010.5757647"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"S\u00e9bastien Bubeck Nicolo Cesa-Bianchi et al. 2012. Regret analysis of stochastic and nonstochastic multi-armed bandit problems. Foundations and Trends\u00ae in Machine Learning 5 1 (2012) 1--122.","DOI":"10.1561\/2200000024"},{"key":"e_1_3_2_1_8_1","unstructured":"Nicol\u00f2 Cesa-Bianchi Tommaso Cesari and Claire Monteleoni. 2020. Cooperative online learning: Keeping your neighbors updated. In Algorithmic learning theory. PMLR 234--250."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-021-09987-4"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2019.2917393"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2021.3065703"},{"key":"e_1_3_2_1_12_1","volume-title":"2020 18th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOPT). IEEE, 1--8.","author":"HasanzadeZonuzy Aria","year":"2020","unstructured":"Aria HasanzadeZonuzy, Dileep Kalathil, and Srinivas Shakkottai. 2020. Reinforcement learning for multi-hop scheduling and routing of real-time flows. In 2020 18th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOPT). IEEE, 1--8."},{"key":"e_1_3_2_1_13_1","volume-title":"AdaConfigure: Reinforcement Learning-Based Adaptive Configuration for Video Analytics Services. In International Conference on Multimedia Modeling. Springer, 245--257","author":"He Zhaoliang","year":"2022","unstructured":"Zhaoliang He, Yuan Wang, Chen Tang, Zhi Wang, Wenwu Zhu, Chenyang Guo, and Zhibo Chen. 2022. AdaConfigure: Reinforcement Learning-Based Adaptive Configuration for Video Analytics Services. In International Conference on Multimedia Modeling. Springer, 245--257."},{"key":"e_1_3_2_1_14_1","unstructured":"I-Hong Hou. 2024. Distributed No-Regret Learning for Multi-Stage Systems with End-to-End Bandit Feedback. arXiv:2404.04509 [cs.LG]"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230574"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.109445"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2010.111910.091238"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2010.2062509"},{"key":"e_1_3_2_1_19_1","first-page":"7813","article-title":"One more step towards reality: Cooperative bandits with imperfect communication","volume":"34","author":"Madhushani Udari","year":"2021","unstructured":"Udari Madhushani, Abhimanyu Dubey, Naomi Leonard, and Alex Pentland. 2021. One more step towards reality: Cooperative bandits with imperfect communication. Advances in Neural Information Processing Systems 34 (2021), 7813--7824.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2014.2363136"},{"key":"e_1_3_2_1_21_1","volume-title":"Decentralized cooperative stochastic bandits. Advances in Neural Information Processing Systems 32","author":"Mart\u00ednez-Rubio David","year":"2019","unstructured":"David Mart\u00ednez-Rubio, Varun Kanade, and Patrick Rebeschini. 2019. Decentralized cooperative stochastic bandits. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_1_22_1","volume-title":"Explore no more: Improved high-probability regret bounds for non-stochastic bandits. Advances in Neural Information Processing Systems 28","author":"Neu Gergely","year":"2015","unstructured":"Gergely Neu. 2015. Explore no more: Improved high-probability regret bounds for non-stochastic bandits. Advances in Neural Information Processing Systems 28 (2015)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3512798.3512817"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.23919\/JCN.2021.000030"},{"key":"e_1_3_2_1_25_1","volume-title":"Online learning and online convex optimization. Foundations and Trends\u00ae in Machine Learning 4, 2","author":"Shalev-Shwartz Shai","year":"2012","unstructured":"Shai Shalev-Shwartz. 2012. Online learning and online convex optimization. Foundations and Trends\u00ae in Machine Learning 4, 2 (2012), 107--194."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2010.100610"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11739"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16108-7_30"},{"key":"e_1_3_2_1_29_1","volume-title":"Conference On Learning Theory. PMLR, 1263--1291","author":"Wei Chen-Yu","year":"2018","unstructured":"Chen-Yu Wei and Haipeng Luo. 2018. More adaptive algorithms for adversarial bandits. In Conference On Learning Theory. PMLR, 1263--1291."},{"key":"e_1_3_2_1_30_1","volume-title":"Soudain: Online Adaptive Profile Configuration for Real-time Video Analytics. In 2021 IEEE\/ACM 29th International Symposium on Quality of Service (IWQOS). IEEE, 1--10","author":"Wu Kun","year":"2021","unstructured":"Kun Wu, Yibo Jin, Weiwei Miao, Zeng Zeng, Zhuzhong Qian, Jingmian Wang, Mingxian Zhou, and Tuo Cao. 2021. Soudain: Online Adaptive Profile Configuration for Real-time Video Analytics. In 2021 IEEE\/ACM 29th International Symposium on Quality of Service (IWQOS). IEEE, 1--10."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2968562"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2021.3106937"}],"event":{"name":"MobiHoc '24: Twenty-fifth International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing","location":"Athens Greece","acronym":"MobiHoc '24","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing"]},"container-title":["Proceedings of the Twenty-fifth International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641512.3686369","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3641512.3686369","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3641512.3686369","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:23Z","timestamp":1750291403000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641512.3686369"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":32,"alternative-id":["10.1145\/3641512.3686369","10.1145\/3641512"],"URL":"https:\/\/doi.org\/10.1145\/3641512.3686369","relation":{},"subject":[],"published":{"date-parts":[[2024,10]]},"assertion":[{"value":"2024-10-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}