Paper published in a book (Scientific congresses and symposiums)
L1-based compression of random forest models
Joly, Arnaud; Schnitzler, François; Geurts, Pierre et al.
2012In 20th European Symposium on Artificial Neural Networks
Peer reviewed
 

Files


Full Text
es2012-43.pdf
Publisher postprint (248.59 kB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
Ensemble of randomized trees; Pruning; L1-norm regularization; LASSO; Supervised learning; Machine Learning; Randomization; Model reduction; Decision tree
Abstract :
[en] Random forests are effective supervised learning methods applicable to large-scale datasets. However, the space complexity of tree ensembles, in terms of their total number of nodes, is often prohibitive, specially in the context of problems with very high-dimensional input spaces. We propose to study their compressibility by applying a L1-based regularization to the set of indicator functions defined by all their nodes. We show experimentally that preserving or even improving the model accuracy while significantly reducing its space complexity is indeed possible.
Research center :
Système et modélisation
GIGA‐R - Giga‐Research - ULiège
Disciplines :
Electrical & electronics engineering
Computer science
Author, co-author :
Joly, Arnaud ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation
Schnitzler, François ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation
Geurts, Pierre ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation
Wehenkel, Louis  ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation
Language :
English
Title :
L1-based compression of random forest models
Publication date :
April 2012
Event name :
European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Event organizer :
Michel Verleysen
Event place :
Bruges, Belgium
Event date :
25 - 27 April 2012
Audience :
International
Main work title :
20th European Symposium on Artificial Neural Networks
Peer reviewed :
Peer reviewed
Funders :
FRIA - Fonds pour la Formation à la Recherche dans l'Industrie et dans l'Agriculture [BE]
Biomagnet IUAP network of the Belgian Science Policy Office
Pascal2 network of excellence of the EC
Available on ORBi :
since 25 February 2012

Statistics


Number of views
678 (82 by ULiège)
Number of downloads
463 (33 by ULiège)

Scopus citations®
 
15
Scopus citations®
without self-citations
14

Bibliography


Similar publications



Contact ORBi