On the depth of decision trees over infinite 1-homogeneous binary information systems
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 de...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-07-01
|
| Series: | Array |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590005621000084 |
| id |
doaj-c7c68ef17993409cb8dbe0a7ab2b6f0f |
|---|---|
| record_format |
Article |
| spelling |
doaj-c7c68ef17993409cb8dbe0a7ab2b6f0f2021-06-11T05:15:38ZengElsevierArray2590-00562021-07-0110100060On the depth of decision trees over infinite 1-homogeneous binary information systemsMikhail Moshkov0Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, 23955-6900, Saudi ArabiaIn 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.http://www.sciencedirect.com/science/article/pii/S2590005621000084Information systemsDecision treesDepth |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Mikhail Moshkov |
| spellingShingle |
Mikhail Moshkov On the depth of decision trees over infinite 1-homogeneous binary information systems Array Information systems Decision trees Depth |
| author_facet |
Mikhail Moshkov |
| author_sort |
Mikhail Moshkov |
| title |
On the depth of decision trees over infinite 1-homogeneous binary information systems |
| title_short |
On the depth of decision trees over infinite 1-homogeneous binary information systems |
| title_full |
On the depth of decision trees over infinite 1-homogeneous binary information systems |
| title_fullStr |
On the depth of decision trees over infinite 1-homogeneous binary information systems |
| title_full_unstemmed |
On the depth of decision trees over infinite 1-homogeneous binary information systems |
| title_sort |
on the depth of decision trees over infinite 1-homogeneous binary information systems |
| publisher |
Elsevier |
| series |
Array |
| issn |
2590-0056 |
| publishDate |
2021-07-01 |
| description |
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. |
| topic |
Information systems Decision trees Depth |
| url |
http://www.sciencedirect.com/science/article/pii/S2590005621000084 |
| work_keys_str_mv |
AT mikhailmoshkov onthedepthofdecisiontreesoverinfinite1homogeneousbinaryinformationsystems |
| _version_ |
1721383410047385600 |