{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T18:07:10Z","timestamp":1725732430152},"publisher-location":"Berlin, Heidelberg","reference-count":21,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642387081"},{"type":"electronic","value":"9783642387098"}],"license":[{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-40988-2_17","type":"book-chapter","created":{"date-parts":[[2013,8,28]],"date-time":"2013-08-28T10:56:40Z","timestamp":1377687400000},"page":"257-272","source":"Crossref","is-referenced-by-count":2,"title":["A Time and Space Efficient Algorithm for Contextual Linear Bandits"],"prefix":"10.1007","author":[{"given":"Jos\u00e9","family":"Bento","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stratis","family":"Ioannidis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S.","family":"Muthukrishnan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinyun","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"17_CR1","unstructured":"Abbasi-Yadkori, Y., P\u00e1l, D., Szepesv\u00e1ri, C.: Improved algorithms for linear stochastic bandits. In: Advances in Neural Information Processing Systems (2011)"},{"key":"17_CR2","unstructured":"Abernethy, J., Hazan, E., Rakhlin, A.: Competing in the dark: An efficient algorithm for bandit linear optimization. In: Proceedings of the 21st Annual Conference on Learning Theory (COLT), vol.\u00a03, p. 3 (2008)"},{"issue":"2","key":"17_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. Machine Learning\u00a047(2), 235\u2013256 (2002)","journal-title":"Machine Learning"},{"key":"17_CR4","first-page":"397","volume":"3","author":"P. Auer","year":"2003","unstructured":"Auer, P.: Using confidence bounds for exploitation-exploration trade-offs. The Journal of Machine Learning Research\u00a03, 397\u2013422 (2003)","journal-title":"The Journal of Machine Learning Research"},{"key":"17_CR5","unstructured":"Auer, P., Cesa-Bianchi, N., Freund, Y., Schapire, R.E.: Gambling in a rigged casino: The adversarial multi-armed bandit problem. In: Proceedings of the 36th Annual Symposium on Foundations of Computer Science, pp. 322\u2013331. IEEE (1995)"},{"issue":"1","key":"17_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.E.: The nonstochastic multiarmed bandit problem. SIAM Journal on Computing\u00a032(1), 48\u201377 (2002)","journal-title":"SIAM Journal on Computing"},{"key":"17_CR7","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1007\/3-540-49097-3_5","volume-title":"Computational Learning Theory","author":"P. Bartlett","year":"1999","unstructured":"Bartlett, P., Ben-David, S.: Hardness results for neural network approximation problems. In: Fischer, P., Simon, H.U. (eds.) EuroCOLT 1999. LNCS (LNAI), vol.\u00a01572, pp. 50\u201362. Springer, Heidelberg (1999)"},{"key":"17_CR8","unstructured":"Beygelzimer, A., Langford, J., Li, L., Reyzin, L., Schapire, R.E.: Contextual bandit algorithms with supervised learning guarantees. In: Proceedings of the International Conference on Artificial Intelligence and Statistics, AISTATS (2011)"},{"key":"17_CR9","unstructured":"Chu, W., Li, L., Reyzin, L., Schapire, R.E.: Contextual bandits with linear payoff functions. In: Proceedings of the International Conference on Artificial Intelligence and Statistics, AISTATS (2011)"},{"key":"17_CR10","unstructured":"Crammer, K., Gentile, C.: Multiclass classification with bandit feedback using adaptive regularization. In: Proceedings of the 28th International Conference on Machine Learning (2011)"},{"key":"17_CR11","unstructured":"Dani, V., Hayes, T.P., Kakade, S.M.: The price of bandit information for online optimization. In: Advances in Neural Information Processing Systems 20, pp. 345\u2013352 (2008)"},{"key":"17_CR12","unstructured":"Dani, V., Hayes, T.P., Kakade, S.M.: Stochastic linear optimization under bandit feedback. In: Proceedings of the 21st Annual Conference on Learning Theory (COLT), pp. 355\u2013366 (2008)"},{"key":"17_CR13","unstructured":"Dudik, M., Hsu, D., Kale, S., Karampatziakis, N., Langford, J., Reyzin, L., Zhang, T.: Efficient optimal learning for contextual bandits. In: UAI (2011)"},{"key":"17_CR14","unstructured":"Hazan, E., Kale, S.: Newtron: an efficient bandit algorithm for online multiclass prediction. In: Advances in Neural Information Processing Systems, NIPS (2011)"},{"issue":"1","key":"17_CR15","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1016\/0304-3975(78)90006-3","volume":"6","author":"D.S. Johnson","year":"1978","unstructured":"Johnson, D.S., Preparata, F.P.: The densest hemisphere problem. Theoretical Computer Science\u00a06(1), 93\u2013107 (1978)","journal-title":"Theoretical Computer Science"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Kakade, S.M., Shalev-Shwartz, S., Tewari, A.: Efficient bandit algorithms for online multiclass prediction. In: Proceedings of the 25th International Conference on Machine Learning, pp. 440\u2013447. ACM (2008)","DOI":"10.1145\/1390156.1390212"},{"key":"17_CR17","unstructured":"Langford, J., Zhang, T.: The epoch-greedy algorithm for contextual multi-armed bandits. In: Advances in Neural Information Processing Systems 20, pp. 1096\u20131103 (2007)"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Li, L., Chu, W., Langford, J., Schapire, R.: A contextual-bandit approach to personalized news article recommendation. In: Proceedings of the 19th International Conference on World Wide Web, pp. 661\u2013670. ACM (2010)","DOI":"10.1145\/1772690.1772758"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Rusmevichientong, P., Tsitsiklis, J.: Linearly parameterized bandits. Mathematics of Operations Research\u00a035(2) (2010)","DOI":"10.1287\/moor.1100.0446"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Sutton, B.: Reinforcement learning, and introduction. MIT Press, Cambdrige (1998)","DOI":"10.1109\/TNN.1998.712192"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Vershynin, R.: Introduction to the non-asymptotic analysis of random matrices. In: Compressed Sensing, Theory and Applications, ch. 5 (2012)","DOI":"10.1017\/CBO9780511794308.006"}],"container-title":["Lecture Notes in Computer Science","Advanced Information Systems Engineering"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-40988-2_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T04:36:20Z","timestamp":1688445380000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-40988-2_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642387081","9783642387098"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-40988-2_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}