. Peter-auer, Y. Nicoì-o-cesa-bianchi, R. E. Freund, O. Schapire, S. Bousquet et al., The nonstochastic multiarmed bandit problem Introduction to statistical learning theory, Haussler, and P. M. Long. Characterizations of learnability for classes of {0...n}-valued functions . Journal of Computer and System Sciences, pp.48-77169, 1995.

. Cbfh-+-97-]-n, Y. Cesa-bianchi, D. Freund, D. P. Haussler, R. Helmbold et al., How to use expert advice Prediction, Learning, and Games Ultraconservative online algorithms for multiclass problems Online multiclass learning by interclass hypothesis sharing From batch to transductive online learning Efficient bandit algorithms for online multiclass prediction Learning quickly when irrelevant attributes abound: A new linearthreshold algorithm The epoch greedy algorithm for contextual multi-armed bandits On larning sets and functions The perceptron : A probabilistic model for information storage and organization in the brain Pattern recognition for conditionally independent data Learning correlated equilibria in games with compact sets of strategies Support vector machines for multi-class patter recognition, Proceedings of the 23rd international conference on Machine learning NIPS Proceedings of the 25th international conference on Machine learning Littlestone and M. Warmuth. The weighted majority algorithm. Information and Computation Advances in Neural Information Processing SystemsSS08] Shai Shalev-Shwartz. Agnostic online learnability Proceedings of the Seventh European Symposium on Artificial Neural Networks, pp.427-485951, 1958.