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).