论文信息 - Learning monotone ku DNF formulas on product distributions - 字舞流文

Learning monotone ku DNF formulas on product distributions

We show how to learn in polynomial time monotone kμ DNF formulas with respect to the uniform distribution. Our result generalizes to product distributions where input bits take on either value with a constant probability.

Yishay Mansour | Thomas R. Hancock | Y. Mansour | T. Hancock

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

[2] Thomas R. Hancock,et al. Learning 2µ DNF Formulas and kµ Decision Trees , 1991, COLT.

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

[4] Leslie G. Valiant,et al. On the learnability of Boolean formulae , 1987, STOC.

[5] Torben Hagerup,et al. A Guided Tour of Chernoff Bounds , 1990, Inf. Process. Lett..

[6] Karsten A. Verbeurgt. Learning DNF under the uniform distribution in quasi-polynomial time , 1990, COLT '90.

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