Optimal randomized classification trees

Autor: Dolores Romero Morales, Rafael Blanquero, Emilio Carrizosa, Cristina Molero-Río
Rok vydání: 2021
Předmět:
FOS: Computer and information sciences
Computer Science - Machine Learning
0209 industrial biotechnology
General Computer Science
Cost-sensitive Classification
Computer science
0211 other engineering and technologies
Decision tree
Machine Learning (stat.ML)
02 engineering and technology
Management Science and Operations Research
Machine learning
computer.software_genre
Nonlinear programming
Machine Learning (cs.LG)
020901 industrial engineering & automation
Statistics - Machine Learning
Classifier (linguistics)
FOS: Mathematics
Classification and Regression Trees
Mathematics - Optimization and Control
Continuous optimization
021103 operations research
Nonlinear Programming
business.industry
Node (networking)
Tree (data structure)
Optimization and Control (math.OC)
Modeling and Simulation
Path (graph theory)
Artificial intelligence
business
computer
Optimal decision
Zdroj: Computers & Operations Research
ISSN: 0305-0548
DOI: 10.1016/j.cor.2021.105281
Popis: Classification and Regression Trees (CARTs) are off-the-shelf techniques in modern Statistics and Machine Learning. CARTs are traditionally built by means of a greedy procedure, sequentially deciding the splitting predictor variable(s) and the associated threshold. This greedy approach trains trees very fast, but, by its nature, their classification accuracy may not be competitive against other state-of-the-art procedures. Moreover, controlling critical issues, such as the misclassification rates in each of the classes, is difficult. To address these shortcomings, optimal decision trees have been recently proposed in the literature, which use discrete decision variables to model the path each observation will follow in the tree. Instead, we propose a new approach based on continuous optimization. Our classifier can be seen as a randomized tree, since at each node of the decision tree a random decision is made. The computational experience reported demonstrates the good performance of our procedure.
Comment: This research has been financed in part by research projects EC H2020 MSCA RISE NeEDS (Grant agreement ID: 822214), FQM-329 and P18-FR-2369 (Junta de Andaluc\'ia), and PID2019-110886RB-I00 (Ministerio de Ciencia, Innovaci\'on y Universidades, Spain). This support is gratefully acknowledged
Databáze: OpenAIRE
Externí odkaz: