| **Kearns, M.** (M. Kearns) -- *The Computational Complexity of Machine Learning* - May 1989 |

| **Kearns, M.** (M. Kearns and L. Pitt) -- *A polynomial-time algorithm for learning k-variable pattern languages from examples* - 1989 |

| **Kearns, M.** (A. Ehrenfeucht, D. Haussler, M. Kearns and L. Valiant) -- *A general lower bound on the number of examples needed for learning* - 1989 |

| **Kearns, M.** (M. Kearns, M. Li, L. Pitt and L. Valiant) -- *On the learnability of Boolean formulae* - 1987 |

| **Kearns, M.** (M. Kearns) -- *Thoughts on Hypothesis Boosting* - December 1988 |

| **Kearns, M.** (M. Kearns, Y. Mansour, D. Ron, R. Rubinfeld, R. Schapire and L. Sellie) -- *On the learnability of discrete distributions* - 1994 |

| **Kearns, M.** (M. Kearns, M. Li, L. Pitt and L. Valiant) -- *Recent Results on Boolean Concept Learning* - June 1987 |

| **Kearns, M.** (Y. Freund, M. Kearns, D. Ron, R. Rubinfeld, R. Schapire and L. Sellie) -- *Efficient learning of typical finite automata from random walks* - 1993 |

| **Kearns, M.** (A. Blum, M. Furst, J. Jackson, M. Kearns, Y. Mansour and S. Rudich) -- *Weakly Learning DNF and Characterizing Statistical Query Learning Using Fourier Analysis* - 1994 |

| **Kearns, M.** (D. Haussler, M. Kearns, N. Littlestone and M. K. Warmuth) -- *Equivalence of Models for Polynomial Learnability* - December 1991 |

| **Kearns, M.** (M. Kearns and L. G. Valiant) -- *Learning Boolean Formulae or Finite Automata is as Hard as Factoring* - 1988 |

| **Kearns, M.** (M. Kearns) -- *Efficient noise-tolerant learning from statistical queries* - 1993 |

| **Kearns, M.** (M. Kearns and L. G. Valiant) -- *Cryptographic limitations on learning Boolean formulae and finite automata* - 1989 |

| **Kearns, M.** (M. Kearns and M. Li) -- *Learning in the presence of malicious errors* - 1993 |

| **Kearns, M.** (D. Haussler, M. Kearns, H. S. Seung and N. Tishby) -- *Rigorous learning curve bounds from statistical mechanics* - 1994 |

| **Kearns, M.** (M. Kearns and Y. Mansour) -- *On the boosting ability of top-down decision tree learning algorithms* - 1999 |