- On Explore-Then-Commit Strategies.
Aurélien Garivier, Emilie Kaufmann and Tor Lattimore. Advances in Neural Processing Systems (NIPS) 2016.
- A Spectral Algorithm with Additive Clustering for the Recovery
of Overlapping Communities in Networks.
Emilie Kaufmann, Thomas Bonald and Marc Lelarge. Algorithmic Learning Theory (ALT) 2016. (slides)
- Maximin Action Identification: a New Bandit Framework for Games,
Aurélien Garivier, Emilie Kaufmann and Wouter M. Koolen. Proceedings of the 29th Conference on Learning Theory (COLT), 2016. (slides)
- Optimal Best-Arm Identification with Fixed Confidence,
Aurélien Garivier and Emilie Kaufmann. Proceedings of the 29th Conference on Learning Theory (COLT), 2016. ( Julia code , Aurelien's slides)
- On the Complexity of A/B Testing.
Emilie Kaufmann, Aurélien Garivier and Olivier Cappé. Proceedings of the 27th Conference on Learning Theory (COLT), 2014. (slides)
- Thompson Sampling for one-dimensional exponential family bandits.
Nathaniel Korda, Emilie Kaufmann and Rémi Munos. in Advances in Neural Information Processing Systems (NIPS), 2013.
- Information complexity in bandit subset selection.
Emilie Kaufmann and Shivaram Kalyanakrishnan, Proceedings of the 26th Conference On Learning Theory (COLT), 2013.
- Thompson Sampling: an asymptotically optimal finite-time analysis.(version longue) Emilie Kaufmann, Nathaniel Korda and Rémi Munos, Proceedings of the 23rd International Conference on Algorithmic Learning Theory (ALT), 2012. (slides)
- On Bayesian Upper Confidence Bounds for Bandits Problems. Emilie Kaufmann, Olivier Cappé and Aurélien Garivier, Fifteenth International Conference on Artificial Intelligence and Statistics (AISTATS), 2012. (poster)
Workshops or conferences without proceedings
- Corrupt Bandits, European Workshop on Reinforcement Learning (EWRL 13), Barcelona, December 2016.
- A novel spectral algorithm for the identification of overlapping communities, ICML workshop on Features and Structures (FEAST), Lille, 2015. (best poster award)
- Information complexity in bandit subset selection : contribution to the workshop
Journées Francophones sur la Planification, la Décision et l'Apprentissage pour la conduite de systèmes (JFPDA), July 2013. (best poster award)
- Improved bandit algorithms: Go Bayesian! : poster at the workshop 'Fête Parisienne in Computation, Inference and Optimization' at IHES, March 2013.
- On the efficiency of Bayesian bandits algorithms from a frequentist point of view contribution to the Workshop 'Bayesian optimization, experimental design, and bandits', NIPS 2011. (poster)
I defended my PhD on October 1st, 2014. The thesis, whose title is Analyse de stratégies bayésiennes et fréquentistes pour l'allocation séquentielle de ressources can be found here
and the slides of the defence there. It was awarded the Prix de thèse Jacques Neveu.