On the depth of decision trees over infinite 1-homogeneous binary information systems
Name:
1-s2.0-S2590005621000084-main.pdf
Size:
366.8Kb
Format:
PDF
Description:
Published Version
Type
ArticleAuthors
Moshkov, Mikhail
KAUST Department
Applied Mathematics and Computational Science ProgramComputer, Electrical and Mathematical Science and Engineering (CEMSE) Division
Extensions of Dynamic Programming, Machine Learning and Discrete Optimization Research Group
Date
2021-07Submitted Date
2020-07-09Permanent link to this record
http://hdl.handle.net/10754/668498Metadata
Show full item recordAbstract
In 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.Citation
Moshkov, M. (2021). On the depth of decision trees over infinite 1-homogeneous binary information systems. Array, 100060. doi:10.1016/j.array.2021.100060Sponsors
Research 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.Publisher
Elsevier BVJournal
ArrayAdditional Links
https://linkinghub.elsevier.com/retrieve/pii/S2590005621000084Scopus Count
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/).