Emilie Kaufmann
Emilie Kaufmann
CNRS & Univ. Lille (CRIStAL)
Verifierad e-postadress på inria.fr - Startsida
TitelCiteras avÅr
Thompson sampling: An asymptotically optimal finite-time analysis
E Kaufmann, N Korda, R Munos
International Conference on Algorithmic Learning Theory, 199-213, 2012
3532012
On Bayesian upper confidence bounds for bandit problems
E Kaufmann, O Cappé, A Garivier
Artificial intelligence and statistics, 592-600, 2012
2252012
On the complexity of best-arm identification in multi-armed bandit models
E Kaufmann, O Cappé, A Garivier
The Journal of Machine Learning Research 17 (1), 1-42, 2016
1822016
Information complexity in bandit subset selection
E Kaufmann, S Kalyanakrishnan
Conference on Learning Theory, 228-251, 2013
852013
Thompson sampling for 1-dimensional exponential family bandits
N Korda, E Kaufmann, R Munos
Advances in neural information processing systems, 1448-1456, 2013
792013
Optimal best arm identification with fixed confidence
A Garivier, E Kaufmann
Conference on Learning Theory, 998-1027, 2016
712016
On the complexity of A/B testing
E Kaufmann, O Cappé, A Garivier
Conference on Learning Theory, 461-481, 2014
302014
On Bayesian index policies for sequential resource allocation
E Kaufmann
arXiv preprint arXiv:1601.01190, 2016
262016
On explore-then-commit strategies
A Garivier, T Lattimore, E Kaufmann
Advances in Neural Information Processing Systems, 784-792, 2016
252016
Analyse de stratégies Bayésiennes et fréquentistes pour l'allocation séquentielle de ressources
E Kaufmann
Paris, ENST, 2014
242014
Multi-player bandits revisited
L Besson, E Kaufmann
arXiv preprint arXiv:1711.02317, 2017
232017
Multi-Armed Bandit Learning in IoT Networks: Learning helps even in non-stationary settings
R Bonnefoi, L Besson, C Moy, E Kaufmann, J Palicot
International Conference on Cognitive Radio Oriented Wireless Networks, 173-185, 2017
192017
Maximin action identification: A new bandit framework for games
A Garivier, E Kaufmann, WM Koolen
Conference on Learning Theory, 1028-1050, 2016
192016
A spectral algorithm with additive clustering for the recovery of overlapping communities in networks
E Kaufmann, T Bonald, M Lelarge
International Conference on Algorithmic Learning Theory, 355-370, 2016
17*2016
Mixture martingales revisited with applications to sequential tests and confidence intervals
E Kaufmann, W Koolen
arXiv preprint arXiv:1811.11419, 2018
122018
Monte-carlo tree search by best arm identification
E Kaufmann, WM Koolen
Advances in Neural Information Processing Systems, 4897-4906, 2017
112017
Learning the distribution with largest mean: two bandit frameworks
E Kaufmann, A Garivier
ESAIM: Proceedings and Surveys 60, 114-131, 2017
102017
Pure exploration in infinitely-armed bandit models with fixed-confidence
M Aziz, J Anderton, E Kaufmann, J Aslam
arXiv preprint arXiv:1803.04665, 2018
92018
Corrupt bandits for preserving local privacy
P Gajane, T Urvoy, E Kaufmann
arXiv preprint arXiv:1708.05033, 2017
92017
On the efficiency of Bayesian bandit algorithms from a frequentist point of view
E Kaufmann, O Cappé, A Garivier
Neural Information Processing Systems (NIPS), 2011
92011
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–20