Learning with maximum-entropy distributions

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