On the depth of decision trees over infinite 1-homogeneous binary information systems
KAUST DepartmentApplied Mathematics and Computational Science Program
Computer, Electrical and Mathematical Science and Engineering (CEMSE) Division
Extensions of Dynamic Programming, Machine Learning and Discrete Optimization Research Group
Permanent link to this recordhttp://hdl.handle.net/10754/668498
MetadataShow full item record
AbstractIn this paper, we study decision trees, which solve problems defined over a specific subclass of infinite information systems, namely: 1-homogeneous binary information systems. It is proved that the minimum depth of a decision tree (defined as a function on the number of attributes in a problem’s description) grows – in the worst case – logarithmically or linearly for each information system in this class. We consider a number of examples of infinite 1-homogeneous binary information systems, including one closely related to the decision trees constructed by the CART algorithm.
CitationMoshkov, M. (2021). On the depth of decision trees over infinite 1-homogeneous binary information systems. Array, 100060. doi:10.1016/j.array.2021.100060
SponsorsResearch reported in this publication was supported by King Abdullah University of Science and Technology (KAUST). The author is thankful to Dr. Michal Mankowski for the helpful comments. The author gratefully acknowledges the useful suggestions of the anonymous reviewers.
Except where otherwise noted, this item's license is described as © 2021 Published by Elsevier Inc. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).