{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T20:00:39Z","timestamp":1776110439024,"version":"3.50.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"1-2","license":[{"start":{"date-parts":[[2008,4,9]],"date-time":"2008-04-09T00:00:00Z","timestamp":1207699200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2008,8]]},"DOI":"10.1007\/s10994-008-5051-0","type":"journal-article","created":{"date-parts":[[2008,4,8]],"date-time":"2008-04-08T12:29:13Z","timestamp":1207657753000},"page":"39-61","source":"Crossref","is-referenced-by-count":94,"title":["Aggregation by exponential weighting, sharp PAC-Bayesian bounds and sparsity"],"prefix":"10.1007","volume":"72","author":[{"given":"A.","family":"Dalalyan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A. B.","family":"Tsybakov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2008,4,9]]},"reference":[{"key":"5051_CR1","unstructured":"Audibert, J.-Y. (2004). Une approche PAC-bay\u00e9sienne de la th\u00e9orie statistique de l\u2019apprentissage. PhD thesis. University of Paris 6."},{"key":"5051_CR2","series-title":"Lecture notes in artificial intelligence","first-page":"392","volume-title":"Proceedings of the 19th annual conference on learning theory, COLT 2006","author":"J.-Y. Audibert","year":"2006","unstructured":"Audibert, J.-Y. (2006). A randomized online learning algorithm for better variance control. In Lecture notes in artificial intelligence : Vol.\u00a04005. Proceedings of the 19th annual conference on learning theory, COLT 2006 (pp. 392\u2013407). Heidelberg: Springer."},{"key":"5051_CR3","unstructured":"Bickel, P. J., Ritov, Y., & Tsybakov, A. B. (2007, submitted). Simultaneous analysis of Lasso and Dantzig selector. Annals of Statistics. http:\/\/arxiv:0801.1158 ."},{"key":"5051_CR4","unstructured":"Bunea, F., Nobel, A.B. (2005). Sequential procedures for aggregating arbitrary estimators of a conditional mean, Preprint Florida State University. ttp:\/\/www.stat.fsu.edu\/~flori ."},{"key":"5051_CR5","series-title":"Lecture notes in artificial intelligence","first-page":"379","volume-title":"Proceedings of 19th annual conference on learning theory, COLT 2006","author":"F. Bunea","year":"2006","unstructured":"Bunea, F., Tsybakov, A. B., & Wegkamp, M. H. (2006). Aggregation and sparsity via \u2113 1-penalized least squares. In Lecture notes in artificial intelligence : Vol.\u00a04005. Proceedings of 19th annual conference on learning theory, COLT 2006 (pp. 379\u2013391). Springer: Heidelberg."},{"key":"5051_CR6","doi-asserted-by":"crossref","first-page":"1674","DOI":"10.1214\/009053606000001587","volume":"35","author":"F. Bunea","year":"2007","unstructured":"Bunea, F., Tsybakov, A. B., & Wegkamp, M. H. (2007a). Aggregation for Gaussian regression. Annals of Statistics, 35, 1674\u20131697.","journal-title":"Annals of Statistics"},{"key":"5051_CR7","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1214\/07-EJS008","volume":"1","author":"F. Bunea","year":"2007","unstructured":"Bunea, F., Tsybakov, A. B., & Wegkamp, M. H. (2007b). Sparsity oracle inequalities for the Lasso. Electronic Journal of Statistics, 1, 169\u2013194.","journal-title":"Electronic Journal of Statistics"},{"key":"5051_CR8","doi-asserted-by":"crossref","first-page":"2313","DOI":"10.1214\/009053606000001523","volume":"35","author":"E. Candes","year":"2007","unstructured":"Candes, E., & Tao, T. (2007). The Dantzig selector: statistical estimation when p is much larger than n (with discussion). Annals of Statistics, 35, 2313\u20132404.","journal-title":"Annals of Statistics"},{"key":"5051_CR9","unstructured":"Catoni, O. (1999). \u201cUniversal\u201d aggregation rules with exact bias bounds. Preprint n.510, Laboratoire de Probabilit\u00e9s et Mod\u00e8les Al\u00e9atoires, Universit\u00e9s Paris 6 and Paris 7. http:\/\/www.proba.jussieu.fr\/mathdoc\/preprints\/index.html#1999 ."},{"key":"5051_CR10","series-title":"Lecture notes in mathematics","doi-asserted-by":"crossref","DOI":"10.1007\/b99352","volume-title":"Ecole d\u2019\u00e9t\u00e9 de Probabilit\u00e9s de Saint-Flour 2001","author":"O. Catoni","year":"2004","unstructured":"Catoni, O., (2004). Statistical learning theory and stochastic optimization. In Lecture notes in mathematics. Ecole d\u2019\u00e9t\u00e9 de Probabilit\u00e9s de Saint-Flour 2001, New York: Springer."},{"key":"5051_CR11","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511546921","volume-title":"Prediction, learning, and games","author":"N. Cesa-Bianchi","year":"2006","unstructured":"Cesa-Bianchi, N., & Lugosi, G. (2006). Prediction, learning, and games. New York: Cambridge University Press."},{"key":"5051_CR12","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1145\/258128.258179","volume":"44","author":"N. Cesa-Bianchi","year":"1997","unstructured":"Cesa-Bianchi, N., Freund, Y., Haussler, D., Helmbold, D. P., Shapire, R., & Warmuth, M. (1997). How to use expert advice. Journal of the ACM, 44, 427\u2013485.","journal-title":"Journal of the ACM"},{"key":"5051_CR13","doi-asserted-by":"crossref","first-page":"2050","DOI":"10.1109\/TIT.2004.833339","volume":"50","author":"N. Cesa-Bianchi","year":"2004","unstructured":"Cesa-Bianchi, N., Conconi, A., & Gentile, G. (2004). On the generalization ability of on-line learning algorithms. IEEE Transactions on Information Theory, 50, 2050\u20132057.","journal-title":"IEEE Transactions on Information Theory"},{"key":"5051_CR14","series-title":"Lecture notes in artificial intelligence","first-page":"97","volume-title":"Proceedings of the 20th annual conference on learning theory (COLT 2007)","author":"A. Dalalyan","year":"2007","unstructured":"Dalalyan, A., & Tsybakov, A. B. (2007). Aggregation by exponential weighting and sharp oracle inequalities. In N. H. Bshouty & C. Gentile (Eds.), Lecture notes in artificial intelligence : Vol.\u00a04539. Proceedings of the 20th annual conference on learning theory (COLT 2007) (pp. 97\u2013111). Berlin: Springer."},{"key":"5051_CR15","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-5320-4","volume-title":"Large deviations techniques and applications","author":"A. Dembo","year":"1998","unstructured":"Dembo, A., & Zeitouni, O. (1998). Large deviations techniques and applications. New York: Springer."},{"key":"5051_CR16","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1109\/TIT.2005.860430","volume":"52","author":"D. L. Donoho","year":"2006","unstructured":"Donoho, D. L., Elad, M., & Temlyakov, V. (2006). Stable recovery of sparse overcomplete representations in the presence of noise. IEEE Transactions on Information Theory, 52, 6\u201318.","journal-title":"IEEE Transactions on Information Theory"},{"key":"5051_CR17","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1214\/009053604000000067","volume":"32","author":"B. Efron","year":"2004","unstructured":"Efron, B., Hastie, T., Johnstone, I., & Tibshirani, R. (2004). Least angle regression. Annals of Statistics, 32, 407\u2013451.","journal-title":"Annals of Statistics"},{"key":"5051_CR18","doi-asserted-by":"crossref","first-page":"971","DOI":"10.3150\/bj\/1106314846","volume":"10","author":"E. Greenshtein","year":"2004","unstructured":"Greenshtein, E., & Ritov, Y. (2004). Persistency in high dimensional linear predictor-selection and the virtue of over-parametrization. Bernoulli, 10, 971\u2013988.","journal-title":"Bernoulli"},{"key":"5051_CR19","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1080\/00401706.1993.10485033","volume":"35","author":"I. E. Frank","year":"1993","unstructured":"Frank, I. E., & Friedman, J. H. (1993). A statistical view of some chemometrics regression tools. Technometrics, 35, 109\u2013148.","journal-title":"Technometrics"},{"key":"5051_CR20","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1007\/s11122-006-0005-2","volume":"41","author":"A. B. Juditsky","year":"2005","unstructured":"Juditsky, A. B., Nazin, A. V., Tsybakov, A. B., & Vayatis, N. (2005). Recursive aggregation of estimators via the Mirror Descent Algorithm with averaging. Problems of Information Transmission, 41, 368\u2013384.","journal-title":"Problems of Information Transmission"},{"key":"5051_CR21","doi-asserted-by":"crossref","unstructured":"Juditsky, A., Rigollet, P., & Tsybakov, A. (2008, to appear). Learning by mirror averaging. Annals of Statistics. https:\/\/hal.ccsd.cnrs.fr\/ccsd-00014097 .","DOI":"10.1214\/07-AOS546"},{"key":"5051_CR22","series-title":"Lecture notes in artificial intelligence","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1007\/3-540-49097-3_13","volume-title":"Proceedings of the fourth European conference on computational learning theory","author":"J. Kivinen","year":"1999","unstructured":"Kivinen, J., & Warmuth, M. K. (1999). Averaging expert predictions. In H. U. Simon & P. Fischer (Eds.), Lecture notes in artificial intelligence : Vol.\u00a01572. Proceedings of the fourth European conference on computational learning theory (pp. 153\u2013167). Berlin: Springer."},{"key":"5051_CR23","unstructured":"Koltchinskii, V. (2006, submitted). Sparsity in penalized empirical risk minimization."},{"key":"5051_CR24","volume-title":"Theory of point estimation","author":"E. L. Lehmann","year":"1998","unstructured":"Lehmann, E. L., & Casella, G. (1998). Theory of point estimation. New York: Springer."},{"key":"5051_CR25","doi-asserted-by":"crossref","first-page":"3396","DOI":"10.1109\/TIT.2006.878172","volume":"52","author":"G. Leung","year":"2006","unstructured":"Leung, G., & Barron, A. (2006). Information theory and mixing least-square regressions. IEEE Transactions on Information Theory, 52, 3396\u20133410.","journal-title":"IEEE Transactions on Information Theory"},{"key":"5051_CR26","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1006\/inco.1994.1009","volume":"108","author":"N. Littlestone","year":"1994","unstructured":"Littlestone, N., & Warmuth, M. K. (1994). The weighted majority algorithm. Information and Computation, 108, 212\u2013261.","journal-title":"Information and Computation"},{"key":"5051_CR27","series-title":"Lecture notes in mathematics","volume-title":"Ecole d\u2019\u00e9t\u00e9 de probabilit\u00e9s de saint-flour","author":"A. Nemirovski","year":"2000","unstructured":"Nemirovski, A. (2000). Topics in non-parametric statistics. In Lecture notes in mathematics : Vol.\u00a01738. Ecole d\u2019\u00e9t\u00e9 de probabilit\u00e9s de saint-flour, 1998. New York: Springer."},{"key":"5051_CR28","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1214\/154957804100000060","volume":"1","author":"J. Obloj","year":"2004","unstructured":"Obloj, J. (2004). The Skorokhod embedding problem and its offspring. Probability Surveys, 1, 321\u2013392.","journal-title":"Probability Surveys"},{"key":"5051_CR29","volume-title":"Limit theorems of probability theory","author":"V. V. Petrov","year":"1995","unstructured":"Petrov, V. V. (1995). Limit theorems of probability theory. Oxford: Clarendon."},{"key":"5051_CR30","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-662-06400-9","volume-title":"Continuous martingales and Brownian motion","author":"D. Revuz","year":"1999","unstructured":"Revuz, D., & Yor, M. (1999). Continuous martingales and Brownian motion. Berlin: Springer."},{"key":"5051_CR31","series-title":"Lecture notes in artificial intelligence","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/978-3-540-45167-9_23","volume-title":"Computational learning theory and kernel machines","author":"A. B. Tsybakov","year":"2003","unstructured":"Tsybakov, A. B. (2003). Optimal rates of aggregation. In B. Sch\u00f6lkopf & M. Warmuth (Eds.), Lecture notes in artificial intelligence : Vol.\u00a02777. Computational learning theory and kernel machines (pp. 303\u2013313). Heidelberg: Springer."},{"key":"5051_CR32","series-title":"Math\u00e9matiques et applications","volume-title":"Introduction \u00e0 l\u2019estimation non-param\u00e9trique","author":"A. B. Tsybakov","year":"2004","unstructured":"Tsybakov, A. B. (2004). Math\u00e9matiques et applications : Vol.\u00a041. Introduction \u00e0 l\u2019estimation non-param\u00e9trique. Berlin: Springer."},{"key":"5051_CR33","first-page":"303","volume":"15","author":"A. B. Tsybakov","year":"2006","unstructured":"Tsybakov, A. B. (2006). Comments on \u201cRegularization in statistics\u201d, by P. Bickel and B. Li. Test, 15, 303\u2013310.","journal-title":"Test"},{"key":"5051_CR34","unstructured":"van de Geer, S. A. (2006). High dimensional generalized linear models and the Lasso (Research report No.\u00a0133). Seminar f\u00fcr Statistik, ETH, Z\u00fcrich."},{"key":"5051_CR35","first-page":"371","volume-title":"Proceedings of the 3rd annual workshop on computational learning theory, COLT1990","author":"V. Vovk","year":"1990","unstructured":"Vovk, V. (1990). Aggregating strategies. In Proceedings of the 3rd annual workshop on computational learning theory, COLT1990 (pp. 371\u2013386). San Mateo: Morgan Kaufmann."},{"key":"5051_CR36","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1111\/j.1751-5823.2001.tb00457.x","volume":"69","author":"V. Vovk","year":"2001","unstructured":"Vovk, V. (2001). Competitive on-line statistics. International Statistical Review, 69, 213\u2013248.","journal-title":"International Statistical Review"},{"key":"5051_CR37","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1006\/jmva.1999.1884","volume":"74","author":"Y. Yang","year":"2000","unstructured":"Yang, Y. (2000). Combining different procedures for adaptive regression. Journal of Multivariate Analysis, 74, 135\u2013161.","journal-title":"Journal of Multivariate Analysis"},{"key":"5051_CR38","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1198\/016214501753168262","volume":"96","author":"Y. Yang","year":"2001","unstructured":"Yang, Y. (2001). Adaptive regression by mixing. Journal of the American Statistical Association, 96, 574\u2013588.","journal-title":"Journal of the American Statistical Association"},{"key":"5051_CR39","first-page":"783","volume":"13","author":"Y. Yang","year":"2003","unstructured":"Yang, Y. (2003). Regression with multiple candidate models: selecting or mixing? Statistica Sinica, 13, 783\u2013809.","journal-title":"Statistica Sinica"},{"key":"5051_CR40","doi-asserted-by":"crossref","first-page":"2180","DOI":"10.1214\/009053606000000704","volume":"34","author":"T. Zhang","year":"2006","unstructured":"Zhang, T. (2006a). From epsilon-entropy to KL-complexity: analysis of minimum information complexity density estimation. Annals of Statistics, 34, 2180\u20132210.","journal-title":"Annals of Statistics"},{"key":"5051_CR41","doi-asserted-by":"crossref","first-page":"1307","DOI":"10.1109\/TIT.2005.864439","volume":"52","author":"T. Zhang","year":"2006","unstructured":"Zhang, T. (2006b). Information theoretical upper and lower bounds for statistical estimation. IEEE Transactions on Information Theory, 52, 1307\u20131321.","journal-title":"IEEE Transactions on Information Theory"},{"key":"5051_CR42","unstructured":"Zhang, C.-H., & Huang, J. (2008, to appear). Model-selection consistency of the Lasso in high-dimensional regression. Annals of Statistics."}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-008-5051-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10994-008-5051-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-008-5051-0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,31]],"date-time":"2019-05-31T21:40:24Z","timestamp":1559338824000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10994-008-5051-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,4,9]]},"references-count":42,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2008,8]]}},"alternative-id":["5051"],"URL":"https:\/\/doi.org\/10.1007\/s10994-008-5051-0","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2008,4,9]]}}}