Learning Random Monotone DNF Under the Uniform Distribution

We show that randomly generated monotone c log(n)-DNF formula can be learned exactly in probabilistic polynomial time. Our notion of randomly generated is with respect to a uniform distribution. To prove this we identify the class of well behaved monotone c log(n)-DNF formulae, and show that almost every monotone DNF formula is well-behaved, and that there exists a probabilistic Turing machine that exactly learns all well behaved monotone c log(n)-DNF formula.

• Type: Conference
• Year: 2008
• Where: COLT
• Authors: Linda Sellie
• Keywords: COLT 2008, Machine Learning, Monotone Dnf Formula, Probabilistic Polynomial Time, Probabilistic Turing Machine