, Multitask Learning with Expert Advice, Proceedings of the 20th Annual Conference on Learning Theory, pp.484-498, 2007.
DOI : 10.1007/978-3-540-72927-3_35
, Competing in the dark: An efficient algorithm for bandit linear optimization Adaptive routing with end-to-end feedback: distributed learning and geometric approaches, Proceedings of the 21st Annual Conference on Learning Theory Proceedings of the 36th Annual ACM Symposium on Theory of Computing, pp.263-274, 2004.
, High-probability regret bounds for bandit online linear optimization, Proceedings of the 21st Annual Conference on Learning Theory, pp.335-342, 2008.
, Universal portfolios with and without transaction costs, Proceedings of the tenth annual conference on Computational learning theory , COLT '97, pp.309-313, 1997.
DOI : 10.1145/267460.267518
, Combinatorial bandits Linear algorithms for online multitask classification, Omnipress Proceedings of the 21st Annual Conference on Learning Theory, 2008.
, The price of bandit information for online optimization, Proceedings of NIPS 2008, 2008.
, Online learning of multiple tasks with a shared loss Genealogical and interacting particle systems with applications Efficient algorithms and minimax bounds for zero-delay lossy source coding Tracking the best of many experts, DM04] P. Del Moral. Feynman-Kac formulae. Probability and its Applications Proceedings of the 18th Annual Conference on Learning Theory, pp.2233-22642337, 2004.
, The on-line shortest path problem under partial monitoring Online geometric optimization in the bandit setting against an adaptive adversary, Learning theory, pp.2369-2403151, 1998.
, Learning across games IVIE-working paper AD 2007-05 Path kernels and multiplicative updates, Vov99] V. Vovk. Derandomizing stochastic prediction strategies. Machine Learning, pp.773-818247, 1999.