Randomly Fallible Teachers: Learning Monotone DNF with an Incomplete Membership Oracle

    loading  Checking for direct PDF access through Ovid

Abstract

We introduce a new fault-tolerant model of algorithmic learning using an equivalence oracle and an incomplete membership oracle, in which the answers to a random subset of the learner's membership queries may be missing. We demonstrate that, with high probability, it is still possible to learn monotone DNF formulas in polynomial time, provided that the fraction of missing answers is bounded by some constant less than one. Even when half the membership queries are expected to yield no information, our algorithm will exactly identify m-term, n-variable monotone DNF formulas with an expected O(mn2) queries. The same task has been shown to require exponential time using equivalence queries alone. We extend the algorithm to handle some one-sided errors, and discuss several other possible error models. It is hoped that this work may lead to a better understanding of the power of membership queries and the effects of faulty teachers on query models of concept learning.

Related Topics

    loading  Loading Related Articles