An optimal algorithm for the thresholding bandit problem A Locatelli, M Gutzeit, A Carpentier International Conference on Machine Learning, 1690-1698, 2016 | 113 | 2016 |

Stochastic simultaneous optimistic optimization M Valko, A Carpentier, R Munos International Conference on Machine Learning, 19-27, 2013 | 113 | 2013 |

Bandit theory meets compressed sensing for high dimensional stochastic linear bandit A Carpentier, R Munos Artificial Intelligence and Statistics, 190-198, 2012 | 105 | 2012 |

Upper-confidence-bound algorithms for active learning in multi-armed bandits A Carpentier, A Lazaric, M Ghavamzadeh, R Munos, P Auer International Conference on Algorithmic Learning Theory, 189-203, 2011 | 93 | 2011 |

Tight (lower) bounds for the fixed budget best arm identification bandit problem A Carpentier, A Locatelli Conference on Learning Theory, 590-604, 2016 | 89 | 2016 |

Simple regret for infinitely many armed bandits A Carpentier, M Valko International Conference on Machine Learning, 1133-1141, 2015 | 71 | 2015 |

Increased expression of regulatory Tr1 cells in recurrent hepatitis C after liver transplantation A Carpentier, F Conti, F Stenard, L Aoudjehane, C Miroux, P Podevin, ... American Journal of Transplantation 9 (9), 2102-2112, 2009 | 51 | 2009 |

Adaptivity to smoothness in x-armed bandits A Locatelli, A Carpentier Conference on Learning Theory, 1463-1492, 2018 | 48 | 2018 |

Revealing graph bandits for maximizing local influence A Carpentier, M Valko Artificial Intelligence and Statistics, 10-18, 2016 | 43 | 2016 |

Extreme bandits A Carpentier, M Valko Advances in Neural Information Processing Systems 27, 2014 | 43 | 2014 |

Two-sample tests for large random graphs using network statistics D Ghoshdastidar, M Gutzeit, A Carpentier, U von Luxburg Conference on Learning Theory, 954-977, 2017 | 39 | 2017 |

Two-sample hypothesis testing for inhomogeneous random graphs D Ghoshdastidar, M Gutzeit, A Carpentier, U Von Luxburg The Annals of Statistics 48 (4), 2208-2229, 2020 | 34 | 2020 |

Finite time analysis of stratified sampling for Monte Carlo A Carpentier, R Munos Advances in Neural Information Processing Systems 24, 2011 | 34 | 2011 |

Rotting bandits are no harder than stochastic ones J Seznec, A Locatelli, A Carpentier, A Lazaric, M Valko The 22nd International Conference on Artificial Intelligence and Statistics …, 2019 | 31 | 2019 |

Uncertainty quantification for matrix compressed sensing and quantum tomography problems A Carpentier, J Eisert, D Gross, R Nickl High Dimensional Probability VIII, 385-430, 2019 | 28 | 2019 |

Adaptive confidence sets for matrix completion A Carpentier, O Klopp, M Löffler, R Nickl Bernoulli 24 (4A), 2429-2460, 2018 | 27 | 2018 |

Adaptivity to noise parameters in nonparametric active learning A Locatelli, A Carpentier, S Kpotufe Proceedings of the 2017 Conference on Learning Theory, PMLR, 2017 | 25 | 2017 |

Linear bandits with stochastic delayed feedback C Vernade, A Carpentier, T Lattimore, G Zappella, B Ermis, M Brueckner International Conference on Machine Learning, 9712-9721, 2020 | 24 | 2020 |

Adaptive estimation of the sparsity in the Gaussian vector model A Carpentier, N Verzelen The Annals of Statistics 47 (1), 93-126, 2019 | 23 | 2019 |

Automatic motor task selection via a bandit algorithm for a brain-controlled button J Fruitet, A Carpentier, R Munos, M Clerc Journal of neural engineering 10 (1), 016012, 2013 | 21 | 2013 |