{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T17:54:43Z","timestamp":1740160483423,"version":"3.37.3"},"reference-count":19,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2022,6,20]],"date-time":"2022-06-20T00:00:00Z","timestamp":1655683200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,6,20]],"date-time":"2022-06-20T00:00:00Z","timestamp":1655683200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Dyn Games Appl"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>We consider a large number of agents collaborating on a multi-armed bandit problem with a large number of arms. The goal is to minimise the regret of each agent in a communication-constrained setting. We present a decentralised algorithm which builds upon and improves the <jats:italic>Gossip-Insert-Eliminate<\/jats:italic> method of Chawla et al. (International conference on artificial intelligence and statistics, pp 3471\u20133481, 2020). We provide a theoretical analysis of the regret incurred which shows that our algorithm is asymptotically optimal. In fact, our regret guarantee matches the asymptotically optimal rate achievable in the full communication setting. Finally, we present empirical results which support our conclusions.<\/jats:p>","DOI":"10.1007\/s13235-022-00451-1","type":"journal-article","created":{"date-parts":[[2022,6,20]],"date-time":"2022-06-20T16:03:12Z","timestamp":1655740992000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Asymptotic Optimality for Decentralised Bandits"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4237-0897","authenticated-orcid":false,"given":"Conor J.","family":"Newton","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ayalvadi","family":"Ganesh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henry W. J.","family":"Reeve","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,6,20]]},"reference":[{"key":"451_CR1","unstructured":"Agarwal M, Aggarwal V, Azizzadenesheli K (2021) Multi-agent multi-armed bandits with limited communication. arXiv preprint arXiv:2102.08462"},{"key":"451_CR2","unstructured":"Cesa-Bianchi N, Cesari T, Monteleoni C (2020) Cooperative online learning: keeping your neighbors updated. In: Algorithmic learning theory, pp 234\u2013250"},{"key":"451_CR3","unstructured":"Chawla R, Sankararaman A, Ganesh A, Shakkottai S (2020) The gossiping insert-eliminate algorithm for multi-agent bandits. In: International conference on artificial intelligence and statistics, pp 3471\u20133481"},{"key":"451_CR4","unstructured":"Dong M, Meng T, Zarchy D, Arslan E, Gilad Y, Godfrey B, Schapira M (2018) PCC vivace: online-learning congestion control. In: 15th USENIX symposium on networked systems design and implementation (NSDI 18), pp 343\u2013356, Renton, WA, USENIX Association"},{"key":"451_CR5","unstructured":"Dubey A (2020) Cooperative multi-agent bandits with heavy tails. In: International conference on machine learning, pp 2730\u20132739. PMLR"},{"key":"451_CR6","unstructured":"Garivier A, Cappe O (2011) The kl-ucb algorithm for bounded stochastic bandits and beyond. In: Proceedings of the 24th annual conference on learning theory, JMLR workshop and conference proceedings, pp 359\u2013376"},{"key":"451_CR7","unstructured":"Giakkoupis G (2011) Tight bounds for rumor spreading in graphs of a given conductance. In: Symposium on theoretical aspects of computer science (STACS2011), vol 9, pp 57\u201368"},{"key":"451_CR8","unstructured":"Jiang J, Sun S, Sekar V, Zhang H (2017) Pytheas: enabling data-driven quality of experience optimization using group-based exploration-exploitation. In: 14th USENIX symposium on networked systems design and implementation (NSDI 17), pp 393\u2013406, Boston, MA, USENIX Association"},{"key":"451_CR9","unstructured":"Kanade V, Liu Z, Radunovic B (2012) Distributed non-stochastic experts. Neurips"},{"issue":"4","key":"451_CR10","doi-asserted-by":"publisher","first-page":"1782","DOI":"10.1109\/TNET.2018.2852361","volume":"26","author":"RK Kolla","year":"2018","unstructured":"Kolla RK, Jagannathan K, Gopalan A (2018) Collaborative learning of stochastic bandits over a social network. IEEE\/ACM Trans Netw 26(4):1782\u20131795","journal-title":"IEEE\/ACM Trans Netw"},{"issue":"1","key":"451_CR11","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/0196-8858(85)90002-8","volume":"6","author":"TL Lai","year":"1985","unstructured":"Lai TL, Robbins H (1985) Asymptotically efficient adaptive allocation rules. Adv Appl Math 6(1):4\u201322","journal-title":"Adv Appl Math"},{"key":"451_CR12","doi-asserted-by":"publisher","DOI":"10.1017\/9781108571401","volume-title":"Bandit algorithms","author":"T Lattimore","year":"2020","unstructured":"Lattimore T, Szepesv\u00e1ri C (2020) Bandit algorithms. Cambridge University Press, Cambridge"},{"key":"451_CR13","volume-title":"Distributed algorithms","author":"NA Lynch","year":"1996","unstructured":"Lynch NA (1996) Distributed algorithms. Elsevier, Amsterdam"},{"key":"451_CR14","unstructured":"Maillard OA, Munos R, Stoltz G (2011) A finite-time analysis of multi-armed bandits problems with kullback-leibler divergences. In: Proceedings of the 24th annual conference on learning theory, pp 497\u2013514. JMLR Workshop and Conference Proceedings"},{"key":"451_CR15","unstructured":"Martinez-Rubio D, Kanade V, Rebeschini P (2018) Decentralized cooperative stochastic bandits. Neurips"},{"key":"451_CR16","doi-asserted-by":"crossref","unstructured":"Pandey S, Agarwal D, Chakrabarti D, Josifovski V (2007) Bandits for taxonomies: a model-based approach. In: Proceedings of the 2007 SIAM international conference on data mining, pp 216\u2013227. SIAM","DOI":"10.1137\/1.9781611972771.20"},{"issue":"3","key":"451_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3366701","volume":"3","author":"A Sankararaman","year":"2019","unstructured":"Sankararaman A, Ganesh A, Shakkottai S (2019) Social learning in multi agent multi armed bandits. Proc ACM Meas Anal Comput Syst 3(3):1\u201335","journal-title":"Proc ACM Meas Anal Comput Syst"},{"key":"451_CR18","unstructured":"Sugawara K, Kazama T, Watanabe T (2004) Foraging behavior of interacting robots with virtual pheromone. In: 2004 IEEE\/RSJ international conference on intelligent robots and systems (IROS) (IEEE Cat. No.04CH37566), vol 3, pp 3074\u20133079"},{"key":"451_CR19","unstructured":"Szorenyi B, Busa-Fekete R, Hegedus I, Ormandi R, Jelasity M, Kegl B (2013) Gossip-based distributed stochastic bandit algorithms. In: International conference on machine learning, pp 19\u201327. PMLR"}],"container-title":["Dynamic Games and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13235-022-00451-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13235-022-00451-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13235-022-00451-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,20]],"date-time":"2022-06-20T16:36:16Z","timestamp":1655742976000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13235-022-00451-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,20]]},"references-count":19,"alternative-id":["451"],"URL":"https:\/\/doi.org\/10.1007\/s13235-022-00451-1","relation":{},"ISSN":["2153-0785","2153-0793"],"issn-type":[{"type":"print","value":"2153-0785"},{"type":"electronic","value":"2153-0793"}],"subject":[],"published":{"date-parts":[[2022,6,20]]},"assertion":[{"value":"4 May 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 June 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}