The weighted majority algorithm N Littlestone, MK Warmuth University of California, Santa Cruz, Computer Research Laboratory, 1989 | 2366 | 1989 |

Learnability and the Vapnik-Chervonenkis dimension A Blumer, A Ehrenfeucht, D Haussler, MK Warmuth Journal of the ACM (JACM) 36 (4), 929-965, 1989 | 2090 | 1989 |

Occam's razor A Blumer, A Ehrenfeucht, D Haussler, MK Warmuth Information processing letters 24 (6), 377-380, 1987 | 1134 | 1987 |

Exponentiated gradient versus gradient descent for linear predictors J Kivinen, MK Warmuth information and computation 132 (1), 1-63, 1997 | 905 | 1997 |

How to use expert advice N Cesa-Bianchi, Y Freund, D Haussler, DP Helmbold, RE Schapire, ... Journal of the ACM (JACM) 44 (3), 427-485, 1997 | 808 | 1997 |

Tracking the best expert M Herbster, MK Warmuth Machine learning 32 (2), 151-178, 1998 | 574 | 1998 |

On‐line portfolio selection using multiplicative updates DP Helmbold, RE Schapire, Y Singer, MK Warmuth Mathematical Finance 8 (4), 325-347, 1998 | 333 | 1998 |

Active learning with support vector machines in the drug discovery process MK Warmuth, J Liao, G Rätsch, M Mathieson, S Putta, C Lemmen Journal of chemical information and computer sciences 43 (2), 667-673, 2003 | 320 | 2003 |

Relative loss bounds for on-line density estimation with the exponential family of distributions KS Azoury, MK Warmuth Machine Learning 43 (3), 211-246, 2001 | 307 | 2001 |

Computing on an anonymous ring H Attiya, M Snir, MK Warmuth Journal of the ACM (JACM) 35 (4), 845-875, 1988 | 288 | 1988 |

Sample compression, learnability, and the Vapnik-Chervonenkis dimension S Floyd, M Warmuth Machine learning 21 (3), 269-304, 1995 | 280 | 1995 |

Using and combining predictors that specialize Y Freund, RE Schapire, Y Singer, MK Warmuth Proceedings of the twenty-ninth annual ACM symposium on Theory of computing …, 1997 | 271 | 1997 |

Finding a Shortest Solution for the N× N Extension of the 15-PUZZLE Is Intractable. D Ratner, MK Warmuth AAAI, 168-172, 1986 | 262 | 1986 |

Classifying learnable geometric concepts with the Vapnik-Chervonenkis dimension A Blumer, A Ehrenfeucht, D Haussler, M Warmuth Proceedings of the eighteenth annual ACM symposium on Theory of computing …, 1986 | 258 | 1986 |

Equivalence of models for polynomial learnability D Haussler, M Kearns, N Littlestone, MK Warmuth Information and Computation 95 (2), 129-161, 1991 | 256 | 1991 |

Relating data compression and learnability N Littlestone, M Warmuth Technical report, University of California, Santa Cruz, 1986 | 252 | 1986 |

On the computational complexity of approximating distributions by probabilistic automata N Abe, MK Warmuth Machine learning 9 (2-3), 205-260, 1992 | 230 | 1992 |

Prediction-preserving reducibility L Pitt, MK Warmuth Journal of Computer and System Sciences 41 (3), 430-467, 1990 | 212 | 1990 |

Matrix exponentiated gradient updates for on-line learning and Bregman projection K Tsuda, G Rätsch, MK Warmuth Journal of Machine Learning Research 6 (Jun), 995-1018, 2005 | 202 | 2005 |

The CMU SPHINX-4 speech recognition system P Lamere, P Kwok, E Gouvea, B Raj, R Singh, W Walker, M Warmuth, ... IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP 2003 …, 2003 | 193 | 2003 |