{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T17:30:33Z","timestamp":1743010233482,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319463780"},{"type":"electronic","value":"9783319463797"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","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":[[2016]]},"DOI":"10.1007\/978-3-319-46379-7_22","type":"book-chapter","created":{"date-parts":[[2016,9,20]],"date-time":"2016-09-20T10:54:33Z","timestamp":1474368873000},"page":"321-336","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["On the Prior Sensitivity of Thompson Sampling"],"prefix":"10.1007","author":[{"given":"Che-Yu","family":"Liu","sequence":"first","affiliation":[]},{"given":"Lihong","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,9,21]]},"reference":[{"key":"22_CR1","unstructured":"Abbasi-Yadkori, Y., P\u00e1l, D., Szepesv\u00e1ri, C.: Improved algorithms for linear stochastic bandits. In: NIPS, pp. 2312\u20132320 (2011)"},{"key":"22_CR2","unstructured":"Agarwal, A., Hsu, D., Kale, S., Langford, J., Li, L., Schapire, R.E.: Taming the monster: a fast and simple algorithm for contextual bandits. In: ICML, pp. 1638\u20131646 (2014)"},{"key":"22_CR3","unstructured":"Agrawal, S., Goyal, N.: Analysis of Thompson sampling for the multi-armed bandit problem. In: COLT, pp. 39.1\u201339.26 (2012)"},{"key":"22_CR4","unstructured":"Agrawal, S., Goyal, N.: Further optimal regret bounds for Thompson sampling. In: AISTATS, pp. 99\u2013107 (2013)"},{"key":"22_CR5","unstructured":"Agrawal, S., Goyal, N.: Thompson sampling for contextual bandits with linear payoffs. In: ICML, pp. 127\u2013135 (2013)"},{"issue":"1","key":"22_CR6","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1137\/S0097539701398375","volume":"32","author":"P Auer","year":"2002","unstructured":"Auer, P., Cesa-Bianchi, N., Freund, Y., Schapire, R.: The non-stochastic multi-armed bandit problem. SIAM J. Comput. 32(1), 48\u201377 (2002)","journal-title":"SIAM J. Comput."},{"key":"22_CR7","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4614-6114-2","volume-title":"Sequential Experimentation in Clinical Trials: Design and Analysis","author":"J Bartroff","year":"2013","unstructured":"Bartroff, J., Lai, T.L., Shih, M.-C.: Sequential Experimentation in Clinical Trials: Design and Analysis, vol. 298. Springer, Heildelberg (2013)"},{"issue":"1","key":"22_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2200000024","volume":"5","author":"S Bubeck","year":"2012","unstructured":"Bubeck, S., Cesa-Bianchi, N.: 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":"22_CR9","doi-asserted-by":"crossref","unstructured":"Bubeck, S., Liu, C.Y.: Prior-free and prior-dependent regret bounds for Thompson sampling. In: NIPS, pp. 638\u2013646 (2013)","DOI":"10.1109\/CISS.2014.6814158"},{"key":"22_CR10","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":"22_CR11","unstructured":"Chapelle, O., Li, L.: An empirical evaluation of Thompson sampling. In: NIPS, pp. 2249\u20132257 (2011)"},{"key":"22_CR12","unstructured":"Chu, W., Li, L., Reyzin, L., Schapire, R.E.: Contextual bandits with linear payoff functions. In: AISTATS, pp. 208\u2013214 (2011)"},{"key":"22_CR13","unstructured":"Gopalan, A., Mannor, S., Mansour, Y.: Thompson sampling for complex online problems. In: ICML, pp. 100\u2013108 (2014)"},{"key":"22_CR14","unstructured":"Graepel, T., Candela, J.Q., Borchert, T., Herbrich, R.: Web-scale Bayesian click-through rate prediction for sponsored search advertising in Microsoft\u2019s Bing search engine. In: ICML, pp. 13\u201320 (2010)"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Gravin, N., Peres, Y., Sivan, B.: Towards optimal algorithms for prediction with expert advice. In: SODA, pp. 528\u2013547 (2016)","DOI":"10.1137\/1.9781611974331.ch39"},{"key":"22_CR16","unstructured":"Guha, S., Munagala, K.: Approximation algorithms for Bayesian multi-armed bandit problems. arXiv preprint arXiv: 1306.3525v2 (2013)"},{"key":"22_CR17","unstructured":"Guha, S., Munagala, K.: Stochastic regret minimization via Thompson sampling. In: COLT, pp. 317\u2013338 (2014)"},{"key":"22_CR18","unstructured":"Honda, J., Takemura, A.: Optimality of Thompson sampling for Gaussian bandits depends on priors. In: AISTATS, pp. 375\u2013383 (2014)"},{"key":"22_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1007\/978-3-642-34106-9_18","volume-title":"Algorithmic Learning Theory","author":"E Kaufmann","year":"2012","unstructured":"Kaufmann, E., Korda, N., Munos, R.: Thompson sampling: an asymptotically optimal finite-time analysis. In: Bshouty, N.H., Stoltz, G., Vayatis, N., Zeugmann, T. (eds.) ALT 2012. LNCS, vol. 7568, pp. 199\u2013213. Springer, Heidelberg (2012)"},{"key":"22_CR20","unstructured":"Komiyama, J., Honda, J., Nakagawa, H.: Optimal regret analysis of Thompson sampling in stochastic multi-armed bandit problem with multiple plays. In: ICML, pp. 1152\u20131161 (2015)"},{"key":"22_CR21","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, 4\u201322 (1985)","journal-title":"Adv. Appl. Math."},{"key":"22_CR22","unstructured":"Lattimore, T.: The pareto regret frontier for bandits. In: NIPS, pp. 208\u2013216 (2015)"},{"key":"22_CR23","unstructured":"Li, L.: Generalized Thompson sampling for contextual bandits. Technical report MSR-TR-2013-136, Microsoft Research (2013)"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Liu, C.Y., Li, L.: On the prior sensitivity of Thompson sampling (2015). arXiv:1506.03378","DOI":"10.1007\/978-3-319-46379-7_22"},{"key":"22_CR25","first-page":"2069","volume":"13","author":"BC May","year":"2012","unstructured":"May, B.C., Korda, N., Lee, A., Leslie, D.S.: Optimistic Bayesian sampling in contextual-bandit problems. J. Mach. Learn. Res. 13, 2069\u20132106 (2012)","journal-title":"J. Mach. Learn. Res."},{"issue":"4","key":"22_CR26","doi-asserted-by":"publisher","first-page":"1221","DOI":"10.1287\/moor.2014.0650","volume":"39","author":"D Russo","year":"2014","unstructured":"Russo, D., Van Roy, B.: Learning to optimize via posterior sampling. Math. Oper. Res. 39(4), 1221\u20131243 (2014)","journal-title":"Math. Oper. Res."},{"issue":"68","key":"22_CR27","first-page":"1","volume":"17","author":"D Russo","year":"2016","unstructured":"Russo, D., Van Roy, B.: An information-theoretic analysis of Thompson sampling. J. Mach. Learn. Res. 17(68), 1\u201330 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"22_CR28","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1002\/asmb.874","volume":"26","author":"SL Scott","year":"2010","unstructured":"Scott, S.L.: A modern Bayesian look at the multi-armed bandit. Appl. Stoch. Models Bus. Ind. 26, 639\u2013658 (2010)","journal-title":"Appl. Stoch. Models Bus. Ind."},{"key":"22_CR29","first-page":"285","volume":"25","author":"W Thompson","year":"1933","unstructured":"Thompson, W.: On the likelihood that one unknown probability exceeds another in view of the evidence of two samples. Bull. Am. Math. Soc. 25, 285\u2013294 (1933)","journal-title":"Bull. Am. Math. Soc."},{"key":"22_CR30","unstructured":"Xia, Y., Li, H., Qin, T., Yu, N., Liu, T.-Y.: Thompson sampling for budgeted multi-armed bandits. In: IJCAI, pp. 3960\u20133966 (2015)"}],"container-title":["Lecture Notes in Computer Science","Algorithmic Learning Theory"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46379-7_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,11]],"date-time":"2024-03-11T14:07:21Z","timestamp":1710166041000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-46379-7_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319463780","9783319463797"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46379-7_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"21 September 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ALT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithmic Learning Theory","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bari","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 October 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 October 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"alt2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}