ICML 2017poster15 citations
Globally Induced Forest: A Prepruning Compression Scheme
Jean-Michel Begon, Arnaud Joly, Pierre Geurts
Abstract
Tree-based ensemble models are heavy memory-wise. An undesired state of affairs considering nowadays datasets, memory-constrained environment and fitting/prediction times. In this paper, we propose the Globally Induced Forest (GIF) to remedy this problem. GIF is a fast prepruning approach to build lightweight ensembles by iteratively deepening the current forest. It mixes local and global optimizations to produce accurate predictions under memory constraints in reasonable time. We show that the proposed method is more than competitive with standard tree-based ensembles under corresponding constraints, and can sometimes even surpass much larger models.
BibTeX
@InProceedings{pmlr-v70-begon17a,
title = {Globally Induced Forest: A Prepruning Compression Scheme},
author = {Jean-Michel Begon and Arnaud Joly and Pierre Geurts},
booktitle = {Proceedings of the 34th International Conference on Machine Learning},
pages = {420--428},
year = {2017},
editor = {Precup, Doina and Teh, Yee Whye},
volume = {70},
series = {Proceedings of Machine Learning Research},
month = {06--11 Aug},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v70/begon17a/begon17a.pdf},
url = {https://proceedings.mlr.press/v70/begon17a.html},
abstract = {Tree-based ensemble models are heavy memory-wise. An undesired state of affairs considering nowadays datasets, memory-constrained environment and fitting/prediction times. In this paper, we propose the Globally Induced Forest (GIF) to remedy this problem. GIF is a fast prepruning approach to build lightweight ensembles by iteratively deepening the current forest. It mixes local and global optimizations to produce accurate predictions under memory constraints in reasonable time. We show that the proposed method is more than competitive with standard tree-based ensembles under corresponding constraints, and can sometimes even surpass much larger models.}
}