A Syntactic characterization of bounded-rank decision trees in terms of decision lsts

Abstract

Decision lists and decision trees are two models of computation for boolean functions. Blum has shown (Information Processing Letters 42 (1992), 183-185) that rank-k decision trees are a subclass of decision lists. Here we identify precisely, by giving a syntactical characterization, the subclass of decision lists which correspond exactly to the class of bounded rank decision trees. Furthermore we give a more general algorithm to recover reduced decision trees from decision lists.