Information theory and an extension of the maximum likelihood principle, pp.267-281, 1973. ,
Transductive and inductive adaptative inference for regression and density estimation, 2006. ,
URL : https://hal.archives-ouvertes.fr/tel-00119593
PAC-Bayesian bounds for randomized empirical risk minimizers, Mathematical Methods of Statistics, vol.17, issue.4, pp.279-304, 2008. ,
DOI : 10.3103/S1066530708040017
URL : https://hal.archives-ouvertes.fr/hal-00354922
Tighter PACbayes bounds, Advances in Neural Information Processing Systems 18, pp.9-16, 2006. ,
PAC-Bayesian statistical learning theory, 2004. ,
Progressive mixture rules are deviation suboptimal, Advances in Neural Information Processing Systems, 2007. ,
Fast learning rates in statistical inference through aggregation, The Annals of Statistics, vol.37, issue.4, pp.1591-1646, 2009. ,
DOI : 10.1214/08-AOS623
URL : https://hal.archives-ouvertes.fr/hal-00139030
Combining PAC-bayesian and generic chaining bounds, Audibert and S. Bubeck. Minimax policies for adversarial and stochastic bandits, pp.863-889, 2007. ,
Regret bounds and minimax policies under partial monitoring, Journal of Machine Learning Research, 2010. ,
URL : https://hal.archives-ouvertes.fr/hal-00654356
Best Arm Identification in Multi- Armed Bandits, Proceedings of the 23th annual conference on Computational Learning Theory (COLT), 2010. ,
URL : https://hal.archives-ouvertes.fr/hal-00654404
Risk bounds in linear regression through PAC-bayesian truncation, 2009. ,
URL : https://hal.archives-ouvertes.fr/hal-00360268
Exploration???exploitation tradeoff using variance estimates in multi-armed bandits, Theoretical Computer Science, vol.410, issue.19, pp.1876-1902, 2009. ,
DOI : 10.1016/j.tcs.2009.01.016
URL : https://hal.archives-ouvertes.fr/hal-00711069
Fast learning rates for plug-in classifiers, The Annals of Statistics, vol.35, issue.2, pp.608-633, 2007. ,
DOI : 10.1214/009053606000001217
URL : https://hal.archives-ouvertes.fr/hal-00160849
Using confidence bounds for exploitation-exploration trade-offs, Journal of Machine Learning Research, vol.3, pp.397-422, 2002. ,
Finite-time analysis of the multiarmed bandit problem, Machine Learning, vol.47, issue.2/3, pp.235-256, 2002. ,
DOI : 10.1023/A:1013689704352
The Nonstochastic Multiarmed Bandit Problem, SIAM Journal on Computing, vol.32, issue.1, pp.48-77, 2002. ,
DOI : 10.1137/S0097539701398375
Improved Rates for the Stochastic Continuum-Armed Bandit Problem, 20th COLT, 2007. ,
DOI : 10.1007/978-3-540-72927-3_33
Characterizing truthful multiarmed bandit mechanisms: extended abstract, Proceedings of the tenth ACM conference on Electronic commerce, pp.79-88, 2009. ,
Consistency of the group Lasso and multiple kernel learning, Journal of Machine Learning Research, vol.9, pp.1179-1225, 2008. ,
URL : https://hal.archives-ouvertes.fr/hal-00164735
Multiple kernel learning, conic duality, and the SMO algorithm, Twenty-first international conference on Machine learning , ICML '04, 2004. ,
DOI : 10.1145/1015330.1015424
Are Bayes Rules Consistent in Information?, Open Problems in Communication and Computation, pp.85-91, 1987. ,
DOI : 10.1007/978-1-4612-4808-8_22
convergence, The Annals of Statistics, vol.27, issue.5, pp.1564-1599, 1999. ,
DOI : 10.1214/aos/1017939142
Local Rademacher complexities, The Annals of Statistics, vol.33, issue.4, pp.1497-1537, 2005. ,
DOI : 10.1214/009053605000000282
Convexity, Classification, and Risk Bounds, Journal of the American Statistical Association, vol.101, issue.473, pp.138-156, 2006. ,
DOI : 10.1198/016214505000000907
URL : http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.15.3497
Adaboost is consistent, J. Mach. Learn. Res, vol.8, pp.2347-2368, 2007. ,
Bandit Problems, The New Palgrave Dictionary of Economics, 2008. ,
DOI : 10.1057/978-1-349-95121-5_2386-1
Bandit problems with infinitely many arms, The Annals of Statistics, vol.25, issue.5, pp.2103-2116, 1997. ,
DOI : 10.1214/aos/1069362389
Minimum Contrast Estimators on Sieves: Exponential Bounds and Rates of Convergence, Bernoulli, vol.4, issue.3, pp.329-375, 1998. ,
DOI : 10.2307/3318720
Minimal penalties for Gaussian model selection. Probability Theory and Related Fields, pp.33-73, 2007. ,
Méthodes de mélange et d'agrégation d'estimateurs en reconnaissance de formes. Application aux arbres de décision, 2001. ,
Theory of Classification: a Survey of Some Recent Advances, ESAIM: Probability and Statistics, vol.9, pp.323-375, 2005. ,
DOI : 10.1051/ps:2005018
URL : https://hal.archives-ouvertes.fr/hal-00017923
Online optimization in X-armed bandits, Advances in Neural Information Processing Systems 21, pp.201-208, 2009. ,
URL : https://hal.archives-ouvertes.fr/inria-00329797
Aggregation for Gaussian regression, 2007. [37] O. Catoni. Statistical learning theory and stochastic optimization, 2001. ,
DOI : 10.1214/009053606000001587
A mixture approach to universal model selection. preprint LMENS 97-30, Available from http, 1997. ,
Universal aggregation rules with exact bias bound ,
A PAC-Bayesian approach to adaptive classification, 2003. ,
PAC-Bayesian supervised classification: the thermodynamics of statistical learning. Lecture Notes series of the IMS, 2007. ,
URL : https://hal.archives-ouvertes.fr/hal-00206119
High confidence estimates of the mean of heavy-tailed real random variables, 2009. ,
URL : https://hal.archives-ouvertes.fr/hal-00423460
Analysis of two gradient-based algorithms for on-line regression, Proceedings of the tenth annual conference on Computational learning theory , COLT '97, pp.392-411, 1999. ,
DOI : 10.1145/267460.267492
How to use expert advice, Journal of the ACM, vol.44, issue.3, pp.427-485, 1997. ,
DOI : 10.1145/258128.258179
On Prediction of Individual Sequences, SSRN Electronic Journal, vol.27, issue.6, pp.1865-1895, 1999. ,
DOI : 10.2139/ssrn.139692
Minimizing Regret With Label Efficient Prediction, IEEE Transactions on Information Theory, vol.51, issue.6, pp.2152-2162, 2005. ,
DOI : 10.1109/TIT.2005.847729
URL : https://hal.archives-ouvertes.fr/hal-00007537
Bandit algorithms for tree search, In Uncertainty in Artificial Intelligence, 2007. ,
URL : https://hal.archives-ouvertes.fr/inria-00150207
An Optimal Algorithm for Monte Carlo Estimation, SIAM Journal on Computing, vol.29, issue.5, pp.1484-1496, 2000. ,
DOI : 10.1137/S0097539797315306
Aggregation by exponential weighting, sharp oracle inequalities and sparsity, Machine Learning, pp.39-61, 2008. ,
Sparse regression learning by aggregation and Langevin Monte-Carlo, 22nd Annual Conference on Learning Theory, 2009. ,
DOI : 10.1016/j.jcss.2011.12.023
URL : https://hal.archives-ouvertes.fr/hal-00362471
The price of truthfulness for pay-perclick auctions, Proceedings of the tenth ACM conference on Electronic commerce, pp.99-106, 2009. ,
A Probabilistic Theory of Pattern Recognition, 1996. ,
DOI : 10.1007/978-1-4612-0711-5
Adaptive sampling methods for scaling up knowledge discovery algorithms, Data Mining and Knowledge Discovery, vol.6, issue.2, pp.131-152, 2002. ,
DOI : 10.1023/A:1014091514039
Central Limit Theorems for Empirical Measures, The Annals of Probability, vol.6, issue.6, pp.899-929, 1978. ,
DOI : 10.1214/aop/1176995384
Action elimination and stopping conditions for the multi-armed bandit and reinforcement learning problems, The Journal of Machine Learning Research, vol.7, pp.1079-1105, 2006. ,
On tail probabilities for martingales. The Annals of Probability, pp.100-118, 1975. ,
A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting, Journal of Computer and System Sciences, vol.55, issue.1, pp.119-139, 1997. ,
DOI : 10.1006/jcss.1997.1504
Exploration exploitation in go: UCT for Monte- Carlo go, Online trading between exploration and exploitation Workshop Twentieth Annual Conference on Neural Information Processing Systems, 2006. ,
URL : https://hal.archives-ouvertes.fr/hal-00115330
PAC-Bayesian learning of linear classifiers, Proceedings of the 26th Annual International Conference on Machine Learning, ICML '09, pp.353-360, 2009. ,
DOI : 10.1145/1553374.1553419
Multi-armed Bandit Allocation Indices Wiley-Interscience series in systems and optimization Regret bounds for gaussian process bandit problems, Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS), 1989. ,
A Distribution-Free Theory of Nonparametric Regression, 2004. ,
DOI : 10.1007/b97848
Adaptive Routing Using Expert Advice, The Computer Journal, vol.49, issue.2, pp.180-189, 2006. ,
DOI : 10.1093/comjnl/bxh168
Sequential prediction of individual sequences under general loss functions, IEEE Transactions on Information Theory, vol.44, issue.5, pp.1906-1925, 1998. ,
DOI : 10.1109/18.705569
Some label efficient learning results, Proceedings of the tenth annual conference on Computational learning theory , COLT '97, pp.218-230, 1997. ,
DOI : 10.1145/267460.267502
URL : http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.179.437
Probability Inequalities for Sums of Bounded Random Variables, Journal of the American Statistical Association, vol.1, issue.301, pp.13-30, 1963. ,
DOI : 10.1214/aoms/1177730491
Adaptation in natural and artificial systems, 1992. ,
The benefit of group sparsity, The Annals of Statistics, vol.38, issue.4, 2009. ,
DOI : 10.1214/09-AOS778
Structured variable selection with sparsity-inducing norms, 2009. ,
URL : https://hal.archives-ouvertes.fr/inria-00377732
Functional aggregation for nonparametric estimation, Ann. Stat, vol.28, pp.681-712, 2000. ,
Learning by mirror averaging, The Annals of Statistics, vol.36, issue.5, pp.2183-2206, 2008. ,
DOI : 10.1214/07-AOS546
URL : https://hal.archives-ouvertes.fr/hal-00341026
Recursive aggregation of estimators by the mirror descent algorithm with averaging. Problems of Information Transmission, pp.368-384, 2005. ,
Exponentiated gradient versus gradient descent for linear predictors. Information and Computation, 1997. ,
DOI : 10.1006/inco.1996.2612
URL : http://doi.org/10.1006/inco.1996.2612
Multi-armed bandit problems in metric spaces, Proceedings of the 40th ACM Symposium on Theory of Computing, 2008. ,
Multi-armed bandits in metric spaces, Proceedings of the fourtieth annual ACM symposium on Theory of computing, STOC 08, pp.681-690, 2008. ,
DOI : 10.1145/1374376.1374475
Nearly tight bounds for the continuum-armed bandit problem, Advances in Neural Information Processing Systems 17, pp.697-704, 2005. ,
Nearly tight bounds for the continuum-armed bandit problem, 2004. ,
Bandit Based Monte-Carlo Planning, Proceedings of the 17th European Conference on Machine Learning (ECML- 2006), pp.282-293, 2006. ,
DOI : 10.1007/11871842_29
URL : http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.102.1296
Local Rademacher complexities and oracle inequalities in risk minimization, The Annals of Statistics, vol.34, issue.6, 2006. ,
DOI : 10.1214/009053606000001019
Sparse recovery in large ensembles of kernel machines, Conference on Learning Theory, COLT, pp.229-238, 2008. ,
PAC-Bayesian Learning of Linear Classifiers, Proceedings of the 26th International Conference on Machine Learning, 2009. ,
PAC- Bayes Bounds for the Risk of the Majority Vote and the Variance of the Gibbs Classifier, Advances in Neural Information Processing Systems, vol.19, p.769, 2007. ,
Asymptotically efficient adaptive allocation rules, Advances in Applied Mathematics, vol.6, issue.1, pp.4-22, 1985. ,
DOI : 10.1016/0196-8858(85)90002-8
When can the two-armed bandit algorithm be trusted?, Annals of Applied Probability, vol.14, issue.3, pp.1424-1454, 2004. ,
URL : https://hal.archives-ouvertes.fr/hal-00102253
Learning the kernel matrix with semidefinite programming An improved predictive accuracy bound for averaging classifiers, Proceedings of the 18th International Conference on Machine Learning, pp.27-72, 2001. ,
PAC-Bayes & margins Advances in neural information processing systems, pp.439-446, 2003. ,
PAC-Bayes risk bounds for stochastic averages and majority votes of sample-compressed classifiers, Journal of Machine Learning Research, vol.8, pp.1461-1487, 2007. ,
Suboptimality of Penalized Empirical Risk Minimization in Classification, Proceedings of the 20th annual conference on Computational Learning Theory (COLT), pp.142-156, 2007. ,
DOI : 10.1007/978-3-540-72927-3_12
Aggregation via empirical risk minimization. Probability Theory and Related Fields, pp.591-613, 2009. ,
The importance of convexity in learning with squared loss, Proceedings of the ninth annual conference on Computational learning theory , COLT '96, pp.1974-1980, 1998. ,
DOI : 10.1145/238061.238082
Sup-norm convergence rate and sign concentration property of Lasso and Dantzig estimators, Electronic Journal of Statistics, vol.2, issue.0, pp.90-102, 2008. ,
DOI : 10.1214/08-EJS177
URL : https://hal.archives-ouvertes.fr/hal-00222251
Taking advantage of sparsity in multi-task learning, Proceedings of the 22th annual conference on Computational Learning Theory (COLT), 2009. ,
On the bayes-risk consistency of regularized boosting methods, Ann. Stat, vol.32, issue.1, pp.30-55, 2004. ,
URL : https://hal.archives-ouvertes.fr/hal-00102140
Some comments on Cp, Technometrics, vol.15, pp.661-675, 1973. ,
Smooth discrimination analysis, Ann. Stat, vol.27, pp.1808-1829, 1999. ,
Hoeffding races: Accelerating model selection search for classification and function approximation, NIPS, pp.59-66, 1993. ,
Some applications of concentration inequalities to statistics, Annales de la facult?? des sciences de Toulouse Math??matiques, vol.9, issue.2, pp.245-303, 2000. ,
DOI : 10.5802/afst.961
Risk bounds for statistical learning, The Annals of Statistics, vol.34, issue.5, pp.2326-2366, 2006. ,
DOI : 10.1214/009053606000000786
URL : http://arxiv.org/abs/math/0702683
Empirical Bernstein Bounds and Sample Variance Penalization, stat, p.21, 1050. ,
PAC-Bayesian model averaging, Proceedings of the twelfth annual conference on Computational learning theory , COLT '99, pp.164-170, 1999. ,
DOI : 10.1145/307400.307435
Simplified PAC-Bayesian Margin Bounds, COLT: Proceedings of the Workshop on Computational Learning Theory, 2003. ,
DOI : 10.1007/978-3-540-45167-9_16
High-dimensional additive modeling, The Annals of Statistics, vol.37, issue.6B, pp.3779-3821, 2009. ,
DOI : 10.1214/09-AOS692
Lasso-type recovery of sparse representations for high-dimensional data, The Annals of Statistics, vol.37, issue.1, pp.246-270, 2009. ,
DOI : 10.1214/07-AOS582
Lower bounds for the empirical minimization algorithm. Information Theory, IEEE Transactions on, vol.54, issue.8, pp.3797-3803, 2008. ,
Universal prediction, IEEE Transactions on Information Theory, vol.44, issue.6, pp.2124-2147, 1998. ,
DOI : 10.1109/18.720534
Learning the kernel function via regularization, Journal of Machine Learning Research, vol.6, issue.2, p.1099, 2006. ,
Empirical Bernstein stopping, Proceedings of the 25th international conference on Machine learning, ICML '08, pp.672-679, 2008. ,
DOI : 10.1145/1390156.1390241
URL : https://hal.archives-ouvertes.fr/hal-00834983
Lectures on probability theory and statistics. Part II: topics in Non-parametric statistics Probability summer school, Saint Flour, 1998. ,
Learning the kernel with hyperkernels, Journal of Machine Learning Research, vol.6, pp.1043-1071, 2005. ,
Sampling methods for action selection in influence diagrams, AAAI/IAAI, pp.378-385, 2000. ,
On the lasso and its dual Minimax rates of estimation for high-dimensional linear regression over lq-balls, Journal of Computational and Graphical Statistics, pp.319-337, 2000. ,
Some aspects of the sequential design of experiments, Bulletin of the American Mathematical Society, vol.58, issue.5, pp.527-535, 1952. ,
DOI : 10.1090/S0002-9904-1952-09620-8
Estimating the dimension of a model. The annals of statistics, pp.461-464, 1978. ,
PAC-Bayesian generalization error bounds for gaussian process classification Informatics report series EDI-INF-RR-0094, 2002. ,
Multi-classification by categorical features via clustering, Proceedings of the 25th international conference on Machine learning, ICML '08, pp.920-927, 2008. ,
DOI : 10.1145/1390156.1390272
Reinforcement Learning: An Introduction, IEEE Transactions on Neural Networks, vol.9, issue.5, 1998. ,
DOI : 10.1109/TNN.1998.712192
Majorizing measures: the generic chaining, The Annals of Probability, vol.24, issue.3, pp.1049-1103, 1996. ,
DOI : 10.1214/aop/1065725175
Anytime many-armed bandit. Conférence francophone sur l'Apprentissage automatique (CAp, 2007. ,
Regression shrinkage and selection via the lasso, J. Roy. Stat. Soc. B, vol.58, pp.267-288, 1994. ,
DOI : 10.1111/j.1467-9868.2011.00771.x
Optimal Rates of Aggregation, Computational Learning Theory and Kernel Machines, pp.303-313, 2003. ,
DOI : 10.1007/978-3-540-45167-9_23
URL : https://hal.archives-ouvertes.fr/hal-00104867
High-dimensional generalized linear models and the lasso, The Annals of Statistics, vol.36, issue.2, p.614, 2008. ,
DOI : 10.1214/009053607000000929
Estimation of Dependences Based on Empirical Data, 1982. ,
AGGREGATING STRATEGIES, COLT '90: Proceedings of the third annual workshop on Computational learning theory, pp.371-386, 1990. ,
DOI : 10.1016/B978-1-55860-146-8.50032-1
A game of prediction with expert advice, Journal of Computer and System Sciences, pp.153-173, 1998. ,
Sharp Thresholds for High-Dimensional and Noisy Sparsity Recovery Using <formula formulatype="inline"><tex Notation="TeX">$\ell _{1}$</tex> </formula>-Constrained Quadratic Programming (Lasso), IEEE Transactions on Information Theory, vol.55, issue.5, pp.2183-2202, 2009. ,
DOI : 10.1109/TIT.2009.2016018
Algorithms for infinitely manyarmed bandits, Advances in Neural Information Processing Systems (NIPS), pp.1729-1736, 2008. ,
Simple sampling techniques for discovery science, IEICE Transactions on Information and Systems, vol.1, pp.19-26, 2000. ,
Combining Different Procedures for Adaptive Regression, Journal of Multivariate Analysis, vol.74, issue.1, pp.135-161, 2000. ,
DOI : 10.1006/jmva.1999.1884
URL : http://doi.org/10.1006/jmva.1999.1884
Adaptive Regression by Mixing, Journal of the American Statistical Association, vol.96, issue.454, pp.574-588, 2001. ,
DOI : 10.1198/016214501753168262
Aggregating regression procedures to improve performance, Bernoulli, vol.10, issue.1, pp.25-47, 2004. ,
DOI : 10.3150/bj/1077544602
How to Better Use Expert Advice, Machine Learning, vol.55, issue.3, pp.271-309, 2004. ,
DOI : 10.1023/B:MACH.0000027784.72823.e4
Model selection and estimation in regression with grouped variables, Journal of the Royal Statistical Society: Series B (Statistical Methodology), vol.58, issue.1, p.49, 2006. ,
DOI : 10.1198/016214502753479356
Information-theoretic upper and lower bounds for statistical estimation, IEEE Transactions on Information Theory, vol.52, issue.4, pp.1307-1321, 2006. ,
DOI : 10.1109/TIT.2005.864439
From ?-entropy to KL-entropy: Analysis of minimum information complexity density estimation, Annals of Statistics, vol.34, issue.5, 2007. ,
On model selection consistency of Lasso, Journal of Machine Learning Research, vol.7, pp.2541-2563, 2006. ,