Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/7803
Title: On phase transitions in learning sparse networks
Authors: HOLLANDERS, Goele 
BEX, Geert Jan 
GYSSENS, Marc 
WESTRA, Ronald 
TUYLS, Karl 
Issue Date: 2007
Publisher: SPRINGER-VERLAG BERLIN
Source: MACHINE LEARNING: ECML 2007, PROCEEDINGS, 4701. p. 591-599
Series/Report: LECTURE NOTES IN COMPUTER SCIENCE
Series/Report no.: 4701
Abstract: In this paper we study the identification of sparse interaction networks as a machine learning problem. Sparsity means that we are provided with a small data set and a high number of unknown components of the system, most of which are zero. Under these circumstances, a model needs to be learned that fits the underlying system, capable of generalization. This corresponds to the student-teacher setting in machine learning. In the first part of this paper we introduce a learning algorithm, based on L-1-minimization, to identify interaction networks from poor data and analyze its dynamics with respect to phase transitions. The efficiency of the algorithm is measured by the generalization error, which represents the probability that the student is a good fit to the teacher. In the second part of this paper we show that from a system with a specific system size value the generalization error of other system sizes can be estimated. A comparison with a set of simulation experiments show a very good fit.
Notes: Hasselt Univ, Dept Math Phys & Comp Sci, Hasselt, Belgium.Hollanders, G, Hasselt Univ, Dept Math Phys & Comp Sci, Hasselt, Belgium.
Keywords: machine learning, sparse network reconstruction, feature identification
Document URI: http://hdl.handle.net/1942/7803
ISBN: 978-3-540-74957-8
ISSN: 0302-9743
DOI: 10.1007/978-3-540-74958-5_57
ISI #: 000249742300053
Category: A1
Type: Journal Contribution
Validations: ecoom 2008
Appears in Collections:Research publications

Files in This Item:
File Description SizeFormat 
ECML2007.pdf192.51 kBAdobe PDFView/Open
Show full item record

Page view(s)

282
checked on Feb 24, 2022

Download(s)

306
checked on Feb 24, 2022

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.