Abstract: | In this paper, we investigate a family of hill-climbing procedures related to GSAT, a greedy random hill-climbing procedure for satisfiability. These procedures are able to solve large and difficult satisfiability problems beyond the range of conventional procedures like Davis-Putnam. We explore the role of greediness, randomness and hill-climbing in the effectiveness of these procedures. We show that neither greediness nor randomness is crucial to GSAT's performance, and that hill-climbing's importance is limited to a short initial phase of search. In addition, we observe some remarkable and possibly universal features of their search for a satisfying truth assignment.
|