{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T04:23:08Z","timestamp":1745986988679,"version":"3.40.4"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030461324"},{"type":"electronic","value":"9783030461331"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-46133-1_11","type":"book-chapter","created":{"date-parts":[[2020,4,30]],"date-time":"2020-04-30T07:08:58Z","timestamp":1588230538000},"page":"167-183","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["BelMan: An Information-Geometric Approach to Stochastic Bandits"],"prefix":"10.1007","author":[{"given":"Debabrota","family":"Basu","sequence":"first","affiliation":[]},{"given":"Pierre","family":"Senellart","sequence":"additional","affiliation":[]},{"given":"St\u00e9phane","family":"Bressan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,4,30]]},"reference":[{"issue":"2","key":"11_CR1","doi-asserted-by":"publisher","first-page":"904","DOI":"10.1137\/100805741","volume":"43","author":"M Agueh","year":"2011","unstructured":"Agueh, M., Carlier, G.: Barycenters in the Wasserstein space. SIAM J. Math. Anal. 43(2), 904\u2013924 (2011)","journal-title":"SIAM J. Math. Anal."},{"key":"11_CR2","doi-asserted-by":"publisher","DOI":"10.1090\/mmono\/191","volume-title":"Methods of Information Geometry Translations of Mathematical Monographs","author":"SI Amari","year":"2007","unstructured":"Amari, S.I., Nagaoka, H.: Methods of Information Geometry Translations of Mathematical Monographs, vol. 191. American Mathematical Society, Providence (2007)"},{"issue":"2\u20133","key":"11_CR3","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1023\/A:1013689704352","volume":"47","author":"P Auer","year":"2002","unstructured":"Auer, P., Cesa-Bianchi, N., Fischer, P.: Finite-time analysis of the multiarmed bandit problem. Mach. Learn. 47(2\u20133), 235\u2013256 (2002)","journal-title":"Mach. Learn."},{"key":"11_CR4","doi-asserted-by":"publisher","unstructured":"Barbaresco, F.: Information geometry of covariance matrix: cartan-siegel homogeneous bounded domains, mostow\/berger fibration and frechet median. In: Nielsen, F., Bhatia, R. (eds.) Matrix Information Geometry, pp. 199\u2013255. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-30232-9_9","DOI":"10.1007\/978-3-642-30232-9_9"},{"key":"11_CR5","unstructured":"Bellman, R.: A problem in the sequential design of experiments. Sankhy\u0101 Ind. J. Stat. (1933\u20131960) 16(3\/4), 221\u2013229 (1956)"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Brown, L.D.: Fundamentals of Statistical Exponential Families: With Applications in Statistical Decision Theory. Institute of Mathematical Statistics (1986)","DOI":"10.1214\/lnms\/1215466757"},{"issue":"1","key":"11_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2200000024","volume":"5","author":"S Bubeck","year":"2012","unstructured":"Bubeck, S., Cesa-Bianchi, N., et al.: Regret analysis of stochastic and nonstochastic multi-armed bandit problems. Found. Trends Mach. Learn. 5(1), 1\u2013122 (2012)","journal-title":"Found. Trends Mach. Learn."},{"key":"11_CR8","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/978-3-642-04414-4_7","volume-title":"Algorithmic Learning Theory","author":"S\u00e9bastien Bubeck","year":"2009","unstructured":"Bubeck, S\u00e9bastien, Munos, R\u00e9mi, Stoltz, Gilles: Pure Exploration in Multi-armed Bandits Problems. In: Gavald\u00e0, Ricard, Lugosi, G\u00e1bor, Zeugmann, Thomas, Zilles, Sandra (eds.) ALT 2009. LNCS (LNAI), vol. 5809, pp. 23\u201337. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-04414-4_7"},{"key":"11_CR9","unstructured":"Capp\u00e9, O., Garivier, A., Kaufmann, \u00c9.: pymaBandits (2012). http:\/\/mloss.org\/software\/view\/415\/"},{"issue":"3","key":"11_CR10","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1214\/aop\/1176993227","volume":"12","author":"I Csisz\u00e1r","year":"1984","unstructured":"Csisz\u00e1r, I.: Sanov property, generalized I-projection and a conditional limit theorem. Ann. Probab. 12(3), 768\u2013793 (1984)","journal-title":"Ann. Probab."},{"key":"11_CR11","volume-title":"Optimal Statistical Decisions, Wiley Classics Library","author":"MH DeGroot","year":"2005","unstructured":"DeGroot, M.H.: Optimal Statistical Decisions, Wiley Classics Library, vol. 82. Wiley, Hoboken (2005)"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Durrett, R.: Probability: Theory and Examples. Cambridge University Press, Cambridge (2010)","DOI":"10.1017\/CBO9780511779398"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Faheem, M., Senellart, P.: Adaptive web crawling through structure-based link classification. In: Proceedings ICADL, pp. 39\u201351. Seoul, December 2015","DOI":"10.1007\/978-3-319-27974-9_5"},{"key":"11_CR14","unstructured":"Garivier, A., Capp\u00e9, O.: The KL-UCB algorithm for bounded stochastic bandits and beyond. In: COLT. pp. 359\u2013376 (2011)"},{"key":"11_CR15","unstructured":"Garivier, A., Lattimore, T., Kaufmann, E.: On explore-then-commit strategies. In: Advances in Neural Information Processing Systems 29, pp. 784\u2013792. Curran Associates, Inc. (2016)"},{"key":"11_CR16","unstructured":"Garivier, A., M\u00e9nard, P., Stoltz, G.: Explore first, exploit next: the true shape of regret in bandit problems. arXiv preprint arXiv:1602.07182 (2016)"},{"issue":"2","key":"11_CR17","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1111\/j.2517-6161.1979.tb01068.x","volume":"41","author":"JC Gittins","year":"1979","unstructured":"Gittins, J.C.: Bandit processes and dynamic allocation indices. J. Roy. Statis. Soc. Ser. B (Methodological) 41(2), 148\u2013177 (1979)","journal-title":"J. Roy. Statis. Soc. Ser. B (Methodological)"},{"key":"11_CR18","unstructured":"Gopalan, A., Mannor, S.: Thompson sampling for learning parameterized Markov decision processes. In: Conference on Learning Theory, pp. 861\u2013898 (2015)"},{"key":"11_CR19","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1109\/TSSC.1968.300117","volume":"4","author":"ET Jaynes","year":"1968","unstructured":"Jaynes, E.T.: Prior probabilities. IEEE Trans. Syst. Sci. Cybern. 4, 227\u2013241 (1968)","journal-title":"IEEE Trans. Syst. Sci. Cybern."},{"issue":"2","key":"11_CR20","doi-asserted-by":"publisher","first-page":"842","DOI":"10.1214\/17-AOS1569","volume":"46","author":"E Kaufmann","year":"2018","unstructured":"Kaufmann, E.: On bayesian index policies for sequential resource allocation. Ann. Stat. 46(2), 842\u2013865 (2018)","journal-title":"Ann. Stat."},{"key":"11_CR21","unstructured":"Kaufmann, E., Capp\u00e9, O., Garivier, A.: On Bayesian upper confidence bounds for bandit problems. In: AISTATS, pp. 592\u2013600 (2012)"},{"key":"11_CR22","unstructured":"Kaufmann, E., Kalyanakrishnan, S.: Information complexity in bandit subset selection. In: COLT, pp. 228\u2013251 (2013)"},{"key":"11_CR23","unstructured":"Kawale, J., Bui, H.H., Kveton, B., Tran-Thanh, L., Chawla, S.: Efficient Thompson sampling for online matrix-factorization recommendation, In: NIPS. pp. 1297\u20131305 (2015)"},{"key":"11_CR24","unstructured":"Krishnasamy, S., Sen, R., Johari, R., Shakkottai, S.: Regret of queueing bandits. In: Advances in Neural Information Processing Systems. pp. 1669\u20131677 (2016)"},{"key":"11_CR25","unstructured":"Kullback, S.: Information Theory and Statistics. Courier Corporation (1997)"},{"issue":"1","key":"11_CR26","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/0196-8858(85)90002-8","volume":"6","author":"TL Lai","year":"1985","unstructured":"Lai, T.L., Robbins, H.: Asymptotically efficient adaptive allocation rules. Adv. Appl. Math. 6(1), 4\u201322 (1985)","journal-title":"Adv. Appl. Math."},{"issue":"1","key":"11_CR27","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1109\/4235.728210","volume":"2","author":"WG Macready","year":"1998","unstructured":"Macready, W.G., Wolpert, D.H.: Bandit problems and the exploration\/exploitation tradeoff. IEEE Trans. Evol. Comput. 2(1), 2\u201322 (1998)","journal-title":"IEEE Trans. Evol. Comput."},{"issue":"2","key":"11_CR28","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1287\/ijoc.1100.0398","volume":"23","author":"J Nino-Mora","year":"2011","unstructured":"Nino-Mora, J.: Computing a classic index for finite-horizon bandits. INFORMS J. Comput. 23(2), 254\u2013267 (2011)","journal-title":"INFORMS J. Comput."},{"key":"11_CR29","unstructured":"Putta, S.R., Tulabandhula, T.: Pure exploration in episodic fixed-horizon Markov decision processes. In: AAMAS, pp. 1703\u20131704 (2017)"},{"issue":"5","key":"11_CR30","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1090\/S0002-9904-1952-09620-8","volume":"58","author":"H Robbins","year":"1952","unstructured":"Robbins, H.: Some aspects of the sequential design of experiments. Bull. Amer. Math. Soc. 58(5), 527\u2013535 (1952)","journal-title":"Bull. Amer. Math. Soc."},{"key":"11_CR31","unstructured":"Russo, D.: Simple Bayesian algorithms for best arm identification. In: Conference on Learning Theory, pp. 1417\u20131418 (2016)"},{"key":"11_CR32","first-page":"1","volume":"17","author":"D Russo","year":"2014","unstructured":"Russo, D., Van Roy, B.: An information-theoretic analysis of Thompson sampling. J. Mach. Learn. Res. 17, 1\u201330 (2014)","journal-title":"J. Mach. Learn. Res."},{"issue":"3","key":"11_CR33","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1214\/aos\/1009210686","volume":"29","author":"X Shen","year":"2001","unstructured":"Shen, X., Wasserman, L., et al.: Rates of convergence of posterior distributions. Ann. Stat. 29(3), 687\u2013714 (2001)","journal-title":"Ann. Stat."},{"issue":"3\u20134","key":"11_CR34","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1093\/biomet\/25.3-4.285","volume":"25","author":"WR Thompson","year":"1933","unstructured":"Thompson, W.R.: On the likelihood that one unknown probability exceeds another in view of the evidence of two samples. Biometrika 25(3\u20134), 285 (1933)","journal-title":"Biometrika"},{"issue":"2","key":"11_CR35","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1214\/aos\/1176324524","volume":"23","author":"WH Wong","year":"1995","unstructured":"Wong, W.H., Shen, X.: Probability inequalities for likelihood ratios and convergence rates of sieve MLES. Ann. Stat. 23(2), 339\u2013362 (1995)","journal-title":"Ann. Stat."}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-46133-1_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T22:05:16Z","timestamp":1745964316000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-46133-1_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030461324","9783030461331"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-46133-1_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"30 April 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"W\u00fcrzburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ecmlpkdd2019.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"733","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"130","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"18% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.04","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5.3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"ECML PKDD Workshops Information: single-blind review, submissions: 200, full papers accepted: 70, short papers accepted: 46","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}