Greedy algorithm with weights for decision tree construction

Handle URI:
http://hdl.handle.net/10754/561592
Title:
Greedy algorithm with weights for decision tree construction
Authors:
Moshkov, Mikhail ( 0000-0003-0085-9483 )
Abstract:
An approximate algorithm for minimization of weighted depth of decision trees is considered. A bound on accuracy of this algorithm is obtained which is unimprovable in general case. Under some natural assumptions on the class NP, the considered algorithm is close (from the point of view of accuracy) to best polynomial approximate algorithms for minimization of weighted depth of decision trees.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Applied Mathematics and Computational Science Program; Extensions of Dynamic Programming, Machine Learning and Discrete Optimization Research Group
Publisher:
IOS Press
Journal:
Fundamenta Informaticae
Issue Date:
1-Dec-2010
DOI:
10.3233/FI-2010-350
Type:
Article
ISSN:
01692968
Sponsors:
This work was partially supported by the KAUST-Stanford AEA program. The author is greatly indebted to the anonymous reviewer for helpful comments and suggestions.
Appears in Collections:
Articles; Applied Mathematics and Computational Science Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorMoshkov, Mikhailen
dc.date.accessioned2015-08-02T09:14:56Zen
dc.date.available2015-08-02T09:14:56Zen
dc.date.issued2010-12-01en
dc.identifier.issn01692968en
dc.identifier.doi10.3233/FI-2010-350en
dc.identifier.urihttp://hdl.handle.net/10754/561592en
dc.description.abstractAn approximate algorithm for minimization of weighted depth of decision trees is considered. A bound on accuracy of this algorithm is obtained which is unimprovable in general case. Under some natural assumptions on the class NP, the considered algorithm is close (from the point of view of accuracy) to best polynomial approximate algorithms for minimization of weighted depth of decision trees.en
dc.description.sponsorshipThis work was partially supported by the KAUST-Stanford AEA program. The author is greatly indebted to the anonymous reviewer for helpful comments and suggestions.en
dc.publisherIOS Pressen
dc.subjectDecision tableen
dc.subjectdecision treeen
dc.subjectgreedy algorithmen
dc.subjectweighten
dc.titleGreedy algorithm with weights for decision tree constructionen
dc.typeArticleen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentApplied Mathematics and Computational Science Programen
dc.contributor.departmentExtensions of Dynamic Programming, Machine Learning and Discrete Optimization Research Groupen
dc.identifier.journalFundamenta Informaticaeen
kaust.authorMoshkov, Mikhailen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.