Greedy algorithm with weights for decision tree construction

Type
Article
Authors
Moshkov, Mikhail cc
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
Date
2010-12-01
Permanent link to this record
http://hdl.handle.net/10754/561592

Metadata
Show full item record
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.
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.
Publisher
IOS Press
Journal
Fundamenta Informaticae
DOI
10.3233/FI-2010-350
Collections
Articles; Applied Mathematics and Computational Science Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division