{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T20:31:40Z","timestamp":1757622700670,"version":"3.44.0"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030864859"},{"type":"electronic","value":"9783030864866"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86486-6_2","type":"book-chapter","created":{"date-parts":[[2021,9,9]],"date-time":"2021-09-09T15:25:48Z","timestamp":1631201148000},"page":"19-34","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Conservative Online Convex Optimization"],"prefix":"10.1007","author":[{"given":"Martino","family":"Bernasconi de Luca","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edoardo","family":"Vittori","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesco","family":"Trov\u00f2","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcello","family":"Restelli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,10]]},"reference":[{"key":"2_CR1","unstructured":"Abernethy, J., Bartlett, P.L., Rakhlin, A., Tewari, A.: Optimal strategies and minimax lower bounds for online convex games. University of California, Berkeley, United States of America, Technical report (2008)"},{"issue":"2\u20133","key":"2_CR2","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."},{"issue":"1\u20132","key":"2_CR3","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/s10998-010-3055-6","volume":"61","author":"P Auer","year":"2010","unstructured":"Auer, P., Ortner, R.: UCB revisited: improved regret bounds for the stochastic multi-armed bandit problem. Period. Math. Hung. 61(1\u20132), 55\u201365 (2010)","journal-title":"Period. Math. Hung."},{"issue":"3","key":"2_CR4","first-page":"357","volume":"19","author":"K Azuma","year":"1967","unstructured":"Azuma, K.: Weighted sums of certain dependent random variables. Tohoku Math. J. Second Ser. 19(3), 357\u2013367 (1967)","journal-title":"Tohoku Math. J. Second Ser."},{"key":"2_CR5","unstructured":"Besson, L., Kaufmann, E.: What doubling tricks can and can\u2019t do for multi-armed bandits. arXiv preprint arXiv:1803.06971 (2018)"},{"issue":"1","key":"2_CR6","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/s10462-009-9109-6","volume":"29","author":"E Blanzieri","year":"2008","unstructured":"Blanzieri, E., Bryl, A.: A survey of learning-based techniques of email spam filtering. Artif. Intell. Rev. 29(1), 63\u201392 (2008)","journal-title":"Artif. Intell. Rev."},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Browne, S.: Beating a moving target: optimal portfolio strategies for outperforming a stochastic benchmark. In: Handbook of the Fundamentals of Financial Decision Making: Part II, pp. 711\u2013730. World Scientific (2013)","DOI":"10.1142\/9789814417358_0035"},{"issue":"9","key":"2_CR8","doi-asserted-by":"publisher","first-page":"2050","DOI":"10.1109\/TIT.2004.833339","volume":"50","author":"N Cesa-Bianchi","year":"2004","unstructured":"Cesa-Bianchi, N., Conconi, A., Gentile, C.: On the generalization ability of on-line learning algorithms. IEEE Trans. Inform. Theory 50(9), 2050\u20132057 (2004)","journal-title":"IEEE Trans. Inform. Theory"},{"key":"2_CR9","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546921","volume-title":"Prediction, Learning, and Games","author":"N Cesa-Bianchi","year":"2006","unstructured":"Cesa-Bianchi, N., Lugosi, G.: Prediction, Learning, and Games. Cambridge University Press, Cambridge (2006)"},{"key":"2_CR10","unstructured":"Cutkosky, A., Orabona, F.: Black-box reductions for parameter-free online learning in banach spaces. In: Conference On Learning Theory (COLT), pp. 1493\u20131529. PMLR (2018)"},{"key":"2_CR11","unstructured":"Dua, D., Graff, C.: UCI machine learning repository (2017). http:\/\/archive.ics.uci.edu\/ml"},{"key":"2_CR12","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12(7) (2011)"},{"key":"2_CR13","unstructured":"Garcelon, E., Ghavamzadeh, M., Lazaric, A., Pirotta, M.: Conservative exploration in reinforcement learning. In: International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 1431\u20131441 (2020)"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Garcelon, E., Ghavamzadeh, M., Lazaric, A., Pirotta, M.: Improved algorithms for conservative exploration in bandits. In: Conference on Artificial Intelligence (AAAI), pp. 3962\u20133969 (2020)","DOI":"10.1609\/aaai.v34i04.5812"},{"issue":"1","key":"2_CR15","first-page":"1437","volume":"16","author":"J Garc\u0131a","year":"2015","unstructured":"Garc\u0131a, J., Fern\u00e1ndez, F.: A comprehensive survey on safe reinforcement learning. J. Mach. Learn. Res. 16(1), 1437\u20131480 (2015)","journal-title":"J. Mach. Learn. Res."},{"issue":"2\u20133","key":"2_CR16","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1007\/s10994-007-5016-8","volume":"69","author":"E Hazan","year":"2007","unstructured":"Hazan, E., Agarwal, A., Kale, S.: Logarithmic regret algorithms for online convex optimization. Mach. Learn. 69(2\u20133), 169\u2013192 (2007)","journal-title":"Mach. Learn."},{"issue":"Apr","key":"2_CR17","first-page":"639","volume":"6","author":"M Hutter","year":"2005","unstructured":"Hutter, M., Poland, J.: Adaptive online prediction by following the perturbed leader. J. Mach. Learn. Res. 6(Apr), 639\u2013660 (2005)","journal-title":"J. Mach. Learn. Res."},{"key":"2_CR18","unstructured":"Kakade, S., Langford, J.: Approximately optimal approximate reinforcement learning. In: International Conference on Machine Learning (ICML), vol. 2, pp. 267\u2013274 (2002)"},{"key":"2_CR19","unstructured":"Kazerouni, A., Ghavamzadeh, M., Yadkori, Y.A., Van Roy, B.: Conservative contextual linear bandits. In: Neural Information Processing Systems (NeurIPS), pp. 3910\u20133919 (2017)"},{"key":"2_CR20","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"2_CR21","unstructured":"Koolen, W.M.: The pareto regret frontier. In: Neural Information Processing Systems (NeurIPS), pp. 863\u2013871 (2013)"},{"key":"2_CR22","unstructured":"Lacoste, A., Luccioni, A., Schmidt, V., Dandres, T.: Quantifying the carbon emissions of machine learning. arXiv preprint arXiv:1910.09700 (2019)"},{"key":"2_CR23","unstructured":"Lattimore, T.: The pareto regret frontier for bandits. In: Neural Information Processing Systems (NeurIPS), pp. 208\u2013216 (2015)"},{"key":"2_CR24","unstructured":"Maas, A., Daly, R.E., Pham, P.T., Huang, D., Ng, A.Y., Potts, C.: Learning word vectors for sentiment analysis. In: Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pp. 142\u2013150 (2011)"},{"key":"2_CR25","unstructured":"Papini, M., Pirotta, M., Restelli, M.: Adaptive batch size for safe policy gradients. In: Neural Information Processing Systems (NeurIPS), pp. 3591\u20133600 (2017)"},{"key":"2_CR26","unstructured":"Papini, M., Pirotta, M., Restelli, M.: Smoothing policies and safe policy gradients. arXiv preprint arXiv:1905.03231 (2019)"},{"issue":"2\u20133","key":"2_CR27","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1007\/s10994-015-5484-1","volume":"100","author":"M Pirotta","year":"2015","unstructured":"Pirotta, M., Restelli, M., Bascetta, L.: Policy gradient in Lipschitz Markov decision processes. Mach. Learn. 100(2\u20133), 255\u2013283 (2015)","journal-title":"Mach. Learn."},{"key":"2_CR28","unstructured":"Pirotta, M., Restelli, M., Pecorino, A., Calandriello, D.: Safe policy iteration. In: International Conference on Machine Learning (ICML), pp. 307\u2013315 (2013)"},{"key":"2_CR29","unstructured":"Reddi, S.J., Kale, S., Kumar, S.: On the convergence of Adam and beyond. arXiv preprint arXiv:1904.09237 (2019)"},{"key":"2_CR30","unstructured":"Sani, A., Neu, G., Lazaric, A.: Exploiting easy data in online optimization. In: Neural Information Processing Systems (NeurIPS) (2014)"},{"key":"2_CR31","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M.I., Moritz, P.: Trust region policy optimization. In: International Conference on Machine Learning (ICML), pp. 1889\u20131897 (2015)"},{"issue":"2","key":"2_CR32","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1561\/2200000018","volume":"4","author":"S Shalev-Shwartz","year":"2011","unstructured":"Shalev-Shwartz, S., et al.: Online learning and online convex optimization. Found. Trends Mach. Learn. 4(2), 107\u2013194 (2011)","journal-title":"Found. Trends Mach. Learn."},{"key":"2_CR33","unstructured":"Streeter, M., McMahan, H.B.: No-regret algorithms for unconstrained online convex optimization. arXiv preprint arXiv:1211.2260 (2012)"},{"key":"2_CR34","unstructured":"Sui, Y., Burdick, J., Yue, Y., et al.: Stagewise safe Bayesian optimization with gaussian processes. In: International Conference on Machine Learning (ICML), pp. 4781\u20134789. PMLR (2018)"},{"key":"2_CR35","unstructured":"Sui, Y., Gotovos, A., Burdick, J., Krause, A.: Safe exploration for optimization with gaussian processes. In: International Conference on Machine Learning (ICML), pp. 997\u20131005. PMLR (2015)"},{"key":"2_CR36","unstructured":"Tange, O.: GNU parallel 2018. Lulu. com (2018)"},{"issue":"2","key":"2_CR37","first-page":"58","volume":"106","author":"A Tsymbal","year":"2004","unstructured":"Tsymbal, A.: The problem of concept drift: definitions and related work. Comput. Sci. Dept. Trinity Coll. Dublin 106(2), 58 (2004)","journal-title":"Comput. Sci. Dept. Trinity Coll. Dublin"},{"key":"2_CR38","unstructured":"Vapnik, V.: Principles of risk minimization for learning theory. In: Neural Information Processing Systems (NeurIPS), pp. 831\u2013838 (1992)"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Vittori, E., de Luca, M.B., Trov\u00f2, F., Restelli, M.: Dealing with transaction costs in portfolio optimization: online gradient descent with momentum. In: ACM International Conference on AI in Finance (ICAIF), pp. 1\u20138 (2020)","DOI":"10.1145\/3383455.3422531"},{"key":"2_CR40","unstructured":"Wu, Y., Shariff, R., Lattimore, T., Szepesv\u00e1ri, C.: Conservative bandits. In: International Conference on Machine Learning (ICML), pp. 1254\u20131262 (2016)"},{"key":"2_CR41","unstructured":"Zinkevich, M.: Online convex programming and generalized infinitesimal gradient ascent. In: International Conference on Machine Learning (ICML), pp. 928\u2013936 (2003)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86486-6_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T22:05:12Z","timestamp":1757369112000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86486-6_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030864859","9783030864866"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86486-6_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"10 September 2021","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":"Bilbao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2021.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"869","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":"210","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":"24% - 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":"3-4","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":"3-9","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":"The conference was held online due to the COVID-19 pandemic.","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)"}}]}}