Conferències i seminaris | Congressos | Grups de recerca | Publicacions | Persones Persones
Sébastien Bubeck
Publicacions
Bandit View on Noisy Optimization, 2010
AUDIBERT, J.Y.; BUBECK, S.J. & MUNOS, R. `Bandit View on Noisy Optimization'. In: *Optimization for Machine Learning*, MIT press, 2010.
Bandits Games and Clustering Foundations, 2010
BUBECK, S. *Bandits Games and Clustering Foundations*. Tesi doctoral, Univ. Lille 1. Defensada el 2010 (candidata al premi Gilles Kahn 2010).
Best Arm Identication in Multi-Armed Bandits, 2010
AUDIBERT, J.Y.; BUBECK, S.J. & MUNOS, R. `Best Arm Identication in Multi-Armed Bandits'. In: *Proceedings of the 23rd Annual Conference on Learning Theory (COLT)*, 2010.
Detection of correlation, 2011
ARIAS-CASTRO, E.; BUBECK, S. & LUGOSI, G. *Detection of correlation*. Preprint (2011)
Good-Turing Bandits, 2011
BUBECK, S. & GARIVIER, A. *Good-Turing Bandits*. Preprint (2011)
Minimax policies for combinatorial prediction games, 2011
AUDIBERT, J.Y.; BUBECK, S. & LUGOSI, G. `Minimax policies for combinatorial prediction games´. In: *Proceedings of COLT 2011, Microtome Publishing* (2011)
Open-Loop Optimistic Planning, 2010
BUBECK, S.J. & MUNOS, R. `Open-Loop Optimistic Planning'. In: *Proceedings of the 23rd Annual Conference on Learning Theory (COLT)*, 2010.
Regret Bounds and Minimax Policies under Partial Monitoring, 2010
AUDIBERT, J.Y. & BUBECK, S. `Regret Bounds and Minimax Policies under Partial Monitoring´. *Journal of Machine Learning Research (JMLR)*; 11, 2635-2686, 2010
The best of both worlds: an adaptive strategy for stochastic and adversarial multi-armed bandits, 2011
BUBECK, S. & SLIVKINS, A. *The best of both worlds: an adaptive strategy for stochastic and adversarial multi-armed bandits*. Preprint (2011)
Altres activitats (conferències, seminaris)
Investigador postdoctoral - Centre de Recerca Matemàtica - Matemàtica aplicada [1/1/2010 - 31/12/2011]
Exposés des prix de thèse SPECIF (3/2/2011)
Al Congrès SPECIF (French conference on computer science), Grénoble -França-, 3 febrer 2011
Investigador postdoctoral - Centre de Recerca Matemàtica - Matemàtica aplicada [1/1/2010 - 31/12/2011]
Minimax Policies for Combinatorial Prediction Games (11/7/2011)
Al COLT (Conference on Learning Theory), Budapest -Hongria-, 11 juliol 2011. Conjuntament amb J.Y. Audibert i G. Lugosi
Investigador postdoctoral - Centre de Recerca Matemàtica - Matemàtica aplicada [1/1/2010 - 31/12/2011]
New (and old) estimators for the mean (19/7/2011)
Al Dagstuhl Workshop, Wadern -Alemanya-, 19 juliol 2011