Finite-time analysis of the multiarmed bandit problem P Auer, N Cesa-Bianchi, P Fischer Machine learning 47 (2), 235-256, 2002 | 7251 | 2002 |

The nonstochastic multiarmed bandit problem P Auer, N Cesa-Bianchi, Y Freund, RE Schapire SIAM Journal on Computing 32 (1), 48-77, 2003 | 2673 | 2003 |

Using confidence bounds for exploitation-exploration trade-offs P Auer Journal of Machine Learning Research 3 (Nov), 397-422, 2002 | 1938 | 2002 |

Near-optimal regret bounds for reinforcement learning T Jaksch, R Ortner, P Auer The Journal of Machine Learning Research 11, 1563-1600, 2010 | 1244* | 2010 |

Gambling in a rigged casino: The adversarial multi-armed bandit problem P Auer, N Cesa-Bianchi, Y Freund, RE Schapire Foundations of Computer Science, 1995. Proceedings., 36th Annual Symposium …, 1995 | 1066 | 1995 |

Gambling in a rigged casino: The adversarial multi-armed bandit problem RE Schapire, N Cesa-Bianchi, P Auer, Y Freund Proceedings of IEEE 36th Annual Foundations of Computer Science, 322-322, 1995 | 1066 | 1995 |

Introduction P Auer, W Maass Algorithmica 22 (1), 1-2, 1998 | 677* | 1998 |

Generic object recognition with boosting A Opelt, A Pinz, M Fussenegger, P Auer IEEE Transactions on Pattern Analysis and Machine Intelligence 28 (3), 416-431, 2006 | 527 | 2006 |

Weak hypotheses and boosting for generic object detection and recognition A Opelt, M Fussenegger, A Pinz, P Auer Computer Vision-ECCV 2004, 71-84, 2004 | 388 | 2004 |

PAC Subset Selection in Stochastic Multi-armed Bandits. S Kalyanakrishnan, A Tewari, P Auer, P Stone ICML 12, 655-662, 2012 | 354 | 2012 |

UCB revisited: Improved regret bounds for the stochastic multi-armed bandit problem P Auer, R Ortner Periodica Mathematica Hungarica 61 (1-2), 55-65, 2010 | 331 | 2010 |

Adaptive and self-confident on-line learning algorithms P Auer, N Cesa-Bianchi, C Gentile Journal of Computer and System Sciences 64 (1), 48-75, 2002 | 305 | 2002 |

Adaptive and self-confident on-line learning algorithms P Auer, N Cesa-Bianchi, C Gentile Journal of Computer and System Sciences 64 (1), 48-75, 2002 | 305 | 2002 |

Logarithmic online regret bounds for undiscounted reinforcement learning P Auer, R Ortner NIPS, 49-56, 2006 | 260 | 2006 |

Degree of approximation results for feedforward networks approximating unknown mappings and their derivatives K Hornik, M Stinchcombe, H White, P Auer Neural Computation 6 (6), 1262-1275, 1994 | 258 | 1994 |

Degree of Approximation Results for Feedforward Networks Approximating Unknown Mapping and Their Derivatives K Honik, M Stinchcombe, H White, P Auer Neural Computation 6 (6), 1262-1275, 1994 | 258 | 1994 |

Improved rates for the stochastic continuum-armed bandit problem P Auer, R Ortner, C Szepesvári Learning Theory, 454-468, 2007 | 251 | 2007 |

A learning rule for very simple universal approximators consisting of a single layer of perceptrons P Auer, H Burgsteiner, W Maass Neural networks 21 (5), 786-795, 2008 | 227 | 2008 |

Exponentially many local minima for single neurons P Auer, M Herbster, MK Warmuth Advances in neural information processing systems, 316-322, 1996 | 210 | 1996 |

The Perceptron algorithm versus Winnow: linear versus logarithmic mistake bounds when few input variables are relevant J Kivinen, MK Warmuth, P Auer Artificial Intelligence 97 (1-2), 325-343, 1997 | 185* | 1997 |