Sebastien Bubeck
Sebastien Bubeck
Sr Principal Research Manager, ML Foundations group, Microsoft Research
Geverifieerd e-mailadres voor microsoft.com - Homepage
Titel
Geciteerd door
Geciteerd door
Jaar
Regret analysis of stochastic and nonstochastic multi-armed bandit problems
S Bubeck, N Cesa-Bianchi
Foundations and Trends in Machine Learning 5, 1-122, 2012
20982012
Convex optimization: Algorithms and complexity
S Bubeck
Foundations and Trends in Machine Learning 8, 231-357, 2014
11612014
Online Optimization in X-Armed Bandits
S Bubeck, G Stoltz, C Szepesvári, R Munos
Advances in Neural Information Processing Systems 21, 201-208, 2008
553*2008
Best arm identification in multi-armed bandits
JY Audibert, S Bubeck, R Munos
COLT 2010, 2010
5442010
Pure exploration in multi-armed bandits problems
S Bubeck, R Munos, G Stoltz
Algorithmic Learning Theory, 23-37, 2009
3782009
X-armed bandits
S Bubeck, R Munos, G Stoltz, C Szepesvári
Journal of Machine Learning Research 12, 1587-1627, 2011
3632011
Minimax policies for adversarial and stochastic bandits
JY Audibert, S Bubeck
COLT 2009, 2009
3522009
lil'UCB: An Optimal Exploration Algorithm for Multi-Armed Bandits
K Jamieson, M Malloy, R Nowak, S Bubeck
COLT 2014, 2013
2722013
Is Q-learning provably efficient?
C Jin, Z Allen-Zhu, S Bubeck, MI Jordan
arXiv preprint arXiv:1807.03765, 2018
2672018
Regret bounds and minimax policies under partial monitoring
JY Audibert, S Bubeck
The Journal of Machine Learning Research 11, 2635-2686, 2010
2032010
Pure exploration in finitely-armed and continuous-armed bandits
S Bubeck, R Munos, G Stoltz
Theoretical Computer Science 412, 1832-1852, 2010
1992010
Regret in online combinatorial optimization
JY Audibert, S Bubeck, G Lugosi
Mathematics of Operations Research 39 (1), 31-45, 2014
1912014
Optimal algorithms for smooth and strongly convex distributed optimization in networks
K Scaman, F Bach, S Bubeck, YT Lee, L Massoulié
international conference on machine learning, 3027-3036, 2017
1772017
Multiple identifications in multi-armed bandits
S Bubeck, T Wang, N Viswanathan
ICML 2012, 2012
1642012
Bandits with heavy tail
S Bubeck, N Cesa-Bianchi, G Lugosi
IEEE Transactions on Information Theory 59 (11), 7711-7717, 2013
1602013
Provably robust deep learning via adversarially trained smoothed classifiers
H Salman, G Yang, J Li, P Zhang, H Zhang, I Razenshteyn, S Bubeck
arXiv preprint arXiv:1906.04584, 2019
1512019
The best of both worlds: Stochastic and adversarial bandits
S Bubeck, A Slivkins
COLT 2012, 2012
1482012
A geometric alternative to Nesterov's accelerated gradient descent
S Bubeck, YT Lee, M Singh
arXiv preprint arXiv:1506.08187, 2015
1252015
Adversarial examples from computational constraints
S Bubeck, YT Lee, E Price, I Razenshteyn
International Conference on Machine Learning, 831-840, 2019
1212019
Towards minimax policies for online linear optimization with bandit feedback
S Bubeck, N Cesa-Bianchi, SM Kakade
COLT 2012, 2012
1092012
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–20