Abstract.
For two disjoint sets of variables, X and Y , and a class of functions C , we define DT(X,Y,C) to be the class of all decision trees over X whose leaves are functions from C over Y . We study the learnability of DT(X,Y,C) using membership and equivalence queries. Boolean decision trees, \(DT(X,\emptyset,\{0,1\})\) , were shown to be exactly learnable by Bshouty but does this imply the learnability of decision trees that have nonboolean leaves? A simple encoding of all possible leaf values will work provided that the size of C is reasonable. Our investigation involves several cases where simple encoding is not feasible, i.e., when |C| is large.
We show how to learn decision trees whose leaves are learnable concepts belonging to a class C , DT(X,Y,C) , when the separation between the variables X and Y is known. A simple algorithm for decision trees whose leaves are constants, \(DT(X, \emptyset, C)\) , is also presented.
Each case above requires at least s separate executions of the algorithm due to Bshouty where s is the number of distinct leaves of the tree but we show that if C is a bounded lattice, \(DT(X,\emptyset,C)\) is learnable using only one execution of this algorithm.
Similar content being viewed by others
Author information
Authors and Affiliations
Additional information
Received September 23, 1995; revised January 15, 1996.
Rights and permissions
About this article
Cite this article
Bshouty, N., Tamon, C. & Wilson, D. On Learning Decision Trees with Large Output Domains. Algorithmica 20, 77–100 (1998). https://doi.org/10.1007/PL00009188
Issue Date:
DOI: https://doi.org/10.1007/PL00009188