Reference : Globally Induced Forest: A Prepruning Compression Scheme
Scientific congresses and symposiums : Paper published in a journal
Engineering, computing & technology : Computer science
http://hdl.handle.net/2268/214279
Globally Induced Forest: A Prepruning Compression Scheme
English
[fr] Globally Induced Forest: une méthode d'élagage
Begon, Jean-Michel mailto [Université de Liège - ULiege > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Algorith. des syst. en interaction avec le monde physique >]
Joly, Arnaud mailto []
Geurts, Pierre mailto [Université de Liège - ULiege > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Algorith. des syst. en interaction avec le monde physique >]
2017
Proceedings of Machine Learning Research
70
Proceedings of the 34th International Conference on Machine Learning
420-428
Yes
No
International
34th International Conference on Machine Learning
du 7 aout 2017 au 11 aout 2017
Sydney
Australie
[en] Compression ; Prepruning ; Random Forest ; Extremely randomized trees ; Iterative model ; stagewise
[en] Tree-based ensemble models are heavy memory- wise. An undesired state of affairs consider- ing 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.
Researchers ; Professionals
http://hdl.handle.net/2268/214279
http://proceedings.mlr.press/v70/begon17a.html

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
gif.pdfArticleAuthor postprint569.37 kBView/Open
Open access
supplementary.pdfSupplementary materialAuthor postprint497.2 kBView/Open

Additional material(s):

File Commentary Size Access
Open access
gif_icml_pres.pdfPresentation929.53 kBView/Open
Open access
gif_icml_poster.pdfPoster343.87 kBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.