论文信息 - Learning with Maximum-Entropy Distributions

Learning with Maximum-Entropy Distributions

We are interested in distributions which are derived as a maximum entropy distribution from a given set of constraints. More specifically, we are interested in the case where the constraints are the expectation of individual and pairs of attributes. For such a given maximum entropy distribution (with some technical restrictions) we develop an efficient learning algorithm for read-once DNF. We extend our results to monotone read-k DNF following the techniques of (Hancock & Mansour, 1991).

Yishay Mansour | Mariano Schain

[1] Athanasios Papoulis,et al. Probability, Random Variables and Stochastic Processes , 1965 .

[2] Yishay Mansour,et al. Learning monotone ku DNF formulas on product distributions , 1991, COLT '91.

[3] Michael Kearns,et al. Efficient noise-tolerant learning from statistical queries , 1993, STOC.

[4] Leslie G. Valiant,et al. Computational limitations on learning from examples , 1988, JACM.

[5] H. Balsters,et al. Learnability with respect to fixed distributions , 1991 .

[6] Balas K. Natarajan,et al. On learning Boolean functions , 1987, STOC.

[7] Thomas M. Cover,et al. Elements of Information Theory , 2005 .

[8] J. Kilian,et al. On the complexity of statistical reasoning , 1995, Proceedings Third Israel Symposium on the Theory of Computing and Systems.

[9] Leslie G. Valiant,et al. A theory of the learnable , 1984, STOC '84.

[10] Nimrod Megiddo,et al. Constructing small sample spaces satisfying given constraints , 1993, SIAM J. Discret. Math..

[11] Bruno O. Shubert,et al. Random variables and stochastic processes , 1979 .

[12] Dana Angluin,et al. When won't membership queries help? , 1991, STOC '91.

[13] David Haussler,et al. Equivalence of models for polynomial learnability , 1988, COLT '88.

[14] C. R. Smith,et al. Maximum-Entropy and Bayesian Methods in Inverse Problems , 1985 .

[15] Leslie G. Valiant,et al. Learning Boolean formulas , 1994, JACM.