A Monte Carlo tree search approach to learning decision trees

Nunes, Cecília; Craene, Mathieu de; Langet, Hélène; Camara, Oscar; Jonsson, Anders, 1973-

doi:http://dx.doi.org/10.1109/ICMLA.2018.00070

A Monte Carlo tree search approach to learning decision trees

Citation

Nunes C, De Craene M, Langet H, Camara O, Jonsson A. A Monte Carlo tree search approach to learning decision trees. In: Proceedings 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018; 2018 Dec 17-20; Orlando, Florida. Piscataway, NJ: Institute of Electrical and Electronics Engineers; 2018. p. 429-35. DOI: 10.1109/ICMLA.2018.00070

Abstract

Decision trees (DTs) are a widely used prediction tool, owing to their interpretability. Standard learning methods follow a locally-optimal approach that trades off prediction performance for computational efficiency. Such methods can however be far from optimal, and it may pay off to spend more computational resources to increase performance. Monte Carlo tree search (MCTS) is an approach to approximate optimal choices in exponentially large search spaces. Since exploring the space of all possible DTs is computationally intractable, we propose a DT learning approach based on MCTS. To bound the branching factor of MCTS, we limit the number of decisions at each level of the search tree, and introduce mechanisms to balance exploration, DT size and the statistical significance of the predictions. To mitigate the computational cost of our method, we employ a move pruning strategy that discards some branches of the search tree, leading to improved performance. The experiments show that our approach outperformed locally optimal search in 20 out of 31 datasets, with a reduction in DT size in most of the cases.

Description

Comunicació presentada a: 17th IEEE International Conference on Machine Learning and Applications (ICMLA) celebrada del 17 al 20 de 2018 a Orlando, Estats Units.