Paper published in a book (Scientific congresses and symposiums)
Learning parameters in discrete naive Bayes models by computing fibers of the parametrization map
Auvray, Vincent; Wehenkel, Louis
2008In NIPS ´08 Workshop: Algebraic and combinatorial methods in machine learning
Peer reviewed
 

Files


Full Text
aml08_auvray_lpdnbmcfpm_01.pdf
Author preprint (93.87 kB)
Download
Annexes
g6y7gH-aml08_auvray_lpdnbmcfpm_01.pdf
Publisher postprint (93.87 kB)
Presentation slides
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
Machine Learning; Graphical Models
Abstract :
[en] Discrete Naive Bayes models are usually defined parametrically with a map from a parameter space to a probability distribution space. First, we present two families of algorithms that compute the set of parameters mapped to a given discrete Naive Bayes distribution satisfying certain technical assumptions. Using these results, we then present two families of parameter learning algorithms that operate by projecting the distribution of observed relative frequencies in a dataset onto the discrete Naive Bayes model considered. They have nice convergence properties, but their computational complexity grows very quickly with the number of hidden classes of the model.
Disciplines :
Computer science
Author, co-author :
Auvray, Vincent
Wehenkel, Louis  ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation
Language :
English
Title :
Learning parameters in discrete naive Bayes models by computing fibers of the parametrization map
Publication date :
20 December 2008
Event name :
NIPS ´08 Workshop: Algebraic and combinatorial methods in machine learning
Audience :
International
Main work title :
NIPS ´08 Workshop: Algebraic and combinatorial methods in machine learning
Peer reviewed :
Peer reviewed
Commentary :
Video lecture and slides available at http://videolectures.net/aml08_auvray_lpdnbmcfpm/
Available on ORBi :
since 11 May 2010

Statistics


Number of views
55 (2 by ULiège)
Number of downloads
43 (0 by ULiège)

Bibliography


Similar publications



Contact ORBi