An introduction to computational learning theory MJ Kearns, UV Vazirani, U Vazirani MIT press, 1994 | 1798 | 1994 |

Cryptographic limitations on learning Boolean formulae and finite automata M Kearns, L Valiant Journal of the ACM (JACM) 41 (1), 67-95, 1994 | 1049 | 1994 |

Near-optimal reinforcement learning in polynomial time M Kearns, S Singh Machine learning 49 (2-3), 209-232, 2002 | 838 | 2002 |

Efficient noise-tolerant learning from statistical queries M Kearns Journal of the ACM (JACM) 45 (6), 983-1006, 1998 | 781 | 1998 |

Graphical models for game theory M Kearns, ML Littman, S Singh arXiv preprint arXiv:1301.2281, 2013 | 659 | 2013 |

A sparse sampling algorithm for near-optimal planning in large Markov decision processes M Kearns, Y Mansour, AY Ng Machine learning 49 (2-3), 193-208, 2002 | 579 | 2002 |

A general lower bound on the number of examples needed for learning A Ehrenfeucht, D Haussler, M Kearns, L Valiant Information and Computation 82 (3), 247-261, 1989 | 546 | 1989 |

Toward efficient agnostic learning MJ Kearns, RE Schapire, LM Sellie Machine Learning 17 (2-3), 115-141, 1994 | 520 | 1994 |

Learning in the presence of malicious errors M Kearns, M Li SIAM Journal on Computing 22 (4), 807-837, 1993 | 506 | 1993 |

Algorithmic stability and sanity-check bounds for leave-one-out cross-validation M Kearns, D Ron Neural computation 11 (6), 1427-1453, 1999 | 468 | 1999 |

Efficient distribution-free learning of probabilistic concepts MJ Kearns, RE Schapire Journal of Computer and System Sciences 48 (3), 464-497, 1994 | 440 | 1994 |

Optimizing dialogue management with reinforcement learning: Experiments with the NJFun system S Singh, D Litman, M Kearns, M Walker Journal of Artificial Intelligence Research 16, 105-133, 2002 | 383 | 2002 |

On the learnability of Boolean formulae M Kearns, M Li, L Pitt, L Valiant Proceedings of the nineteenth annual ACM symposium on Theory of computing …, 1987 | 373 | 1987 |

On the complexity of teaching SA Goldman, MJ Kearns | 341 | 1992 |

Modeling the IT value paradox ME Thatcher, DE Pingry Communications of the ACM 50 (8), 41-45, 2007 | 304* | 2007 |

Bounds on the sample complexity of Bayesian learning using information theory and the VC dimension D Haussler, M Kearns, RE Schapire Machine learning 14 (1), 83-113, 1994 | 297 | 1994 |

Nash Convergence of Gradient Dynamics in General-Sum Games. SP Singh, MJ Kearns, Y Mansour UAI, 541-548, 2000 | 291 | 2000 |

An experimental study of the coloring problem on human subject networks M Kearns, S Suri, N Montfort science 313 (5788), 824-827, 2006 | 282 | 2006 |

Cryptographic primitives based on hard learning problems A Blum, M Furst, M Kearns, RJ Lipton Annual International Cryptology Conference, 278-291, 1993 | 281 | 1993 |

On the learnability of discrete distributions M Kearns, Y Mansour, D Ron, R Rubinfeld, RE Schapire, L Sellie Proceedings of the twenty-sixth annual ACM symposium on Theory of computing …, 1994 | 278 | 1994 |