@ARTICLE{martinez06using,
author = {Gonzalo Mart{\'{\i}}nez-Mu{\~n}oz and Alberto Su{\'a}rez},
title = {Using Boosting to Prune Bagging Ensembles},
journal = {Pattern Recognition Letters},
pages = {156--165},
volume = {28},
year = {2007},
number = {1},
abstract = {Boosting is used to determine the order in which classifiers
are aggregated in a bagging ensemble. Early stopping in the aggregation
of the classifiers in the ordered bagging ensemble allows the identification
of subensembles that require less memory for storage, classify faster and
can improve the generalization accuracy of the original bagging ensemble.
In all the classification problems investigated pruned ensembles with 20%
of the original classifiers show statistically significant improvements
over bagging. In problems where boosting is superior to bagging, these
improvements are not sufficient to reach the accuracy of the corresponding
boosting ensembles. However, ensemble pruning preserves the performance of
bagging in noisy classification tasks, where boosting often has larger
generalization errors. Therefore, pruned bagging should generally be
preferred to complete bagging and, if no information about the level of
noise is available, it is a robust alternative to AdaBoost.}
}
@ARTICLE{martinez05switching,
author = {Martinez-Munoz, G. and Suarez, A.},
title = {Switching class labels to generate classification ensembles},
journal = {PATTERN RECOGNITION},
year = {2005},
volume = {38},
pages = {1483--1494},
number = {10},
abstract = {Ensembles that combine the decisions of classifiers generated by using
perturbed versions of the training set where the classes of the training
examples are randomly switched can produce a significant error reduction,
provided that large numbers of units and high class switching rates
are used. The classifiers generated by this procedure have statistically
uncorrelated errors in the training set. Hence, the ensembles they
form exhibit a similar dependence of the training error on ensemble
size, independently of the classification problem. In particular,
for binary classification problems, the classification performance
of the ensemble on the training data can be analysed in terms of
a Bernoulli process. Experiments on several UCI datasets demonstrate
the improvements in classification accuracy that can be obtained
using these class-switching ensembles. (c) 2005 Pattern Recognition
Society. Published by Elsevier Ltd. All rights reserved.},
}
@ARTICLE{martinez04using,
author = {Gonzalo Mart{\'{\i}}nez-Mu{\~n}oz and Alberto Su{\'a}rez},
title = {Using All Data to Generate Decision Tree Ensembles},
journal = {IEEE Transactions on Systems, Man and Cybernetics part {C}},
year = {2004},
volume = {34},
pages = {393--397},
number = {4}
}
@INPROCEEDINGS{garcia06evaluation,
author = {Sergio Garc\'{\i}a-Moratilla and Gonzalo Martinez-Munoz and Alberto Suarez},
title = {Evaluation of Decision Tree Pruning with Subadditive Penalties},
booktitle = {Intelligent Data Engineering and Automated Learning - IDEAL 2006},
pages = {995--1002},
year = {2006},
abstract = {Recent work on decision tree pruning[1] has brought to the attention
of the machine learning community the fact that, in classification problems,
the use of subadditive penalties in cost-complexity pruning has a stronger
theoretical basis than the usual additive penalty terms. We implement
cost-complexity pruning algorithms with general size-dependent penalties to
confirm the results of[1] . Namely, that the family of pruned subtrees
selected by pruning with a subadditive penalty of increasing strength is
a subset of the family selected using additive penalties. Consequently,
this family of pruned trees is unique, it is nested and it can be computed
efficiently. However, in spite of the better theoretical grounding of
cost-complexity pruning with subadditive penalties, we found no systematic
improvements in the generalization performance of the final classification
tree selected by cross-validation using subadditive penalties instead of the
commonly used additive ones.}
}
@INPROCEEDINGS{martinez06building,
author = {Gonzalo Mart\'{\i}nez-Mu\~noz and
Aitor S\'anchez-Mart\'{\i}nez and
Daniel Hern\'andez-Lobato and
Alberto Su\'arez}
title = {Building Ensembles of Neural Networks with Class-Switching},
booktitle = {Artificial Neural Networks - ICANN 2006},
pages = {178--187},
year = {2006}
}
@INPROCEEDINGS{martinez06pruning,
author = {Gonzalo Mart\'{\i}nez-Mu\~{n}oz and Alberto Su\'{a}rez},
title = {Pruning in ordered bagging ensembles},
booktitle = {ICML '06: Proceedings of the 23rd international conference on Machine learning},
year = {2006},
isbn = {1-59593-383-2},
pages = {609--616},
location = {Pittsburgh, Pennsylvania},
doi = {http://doi.acm.org/10.1145/1143844.1143921},
publisher = {ACM Press},
address = {New York, NY, USA},
abstract = {We present a novel ensemble pruning method based on reordering
the classifiers obtained from bagging and then selecting a subset for
aggregation. Ordering the classifiers generated in bagging makes it possible
to build subensembles of increasing size by including first those classifiers
that are expected to perform best when aggregated. Ensemble pruning is achieved
by halting the aggregation process before all the classifiers generated are
included into the ensemble. Pruned subensembles containing between 15% and 30% of
the initial pool of classifiers, besides being smaller, improve the generalization
performance of the full bagging ensemble in the classification problems investigated.}
}
@inproceedings{hernandez06pruning,
title = {Pruning in Ordered Regression Bagging Ensembles},
author = {Hern\'andez-Lobato, D.; Mart\'{\i}nez-Mu\~noz, G.; Su\'arez, A.},
booktitle = {Neural Networks, 2006. IJCNN '06. International Joint Conference on},
year = {2006},
pages = {1266--1273},
abstract = {An efficient procedure for pruning regression ensembles is introduced.
Starting from a bagging ensemble, pruning proceeds by ordering the regressors in
the original ensemble and then selecting a subset for aggregation. Ensembles of
increasing size are built by including first the regressors that perform best
when aggregated. This strategy gives an approximate solution to the problem of
extracting from the original ensemble the minimum error subensemble, which we
prove to be NP-hard. Experiments show that pruned ensembles with only 20% of the
initial regressors achieve better generalization accuracies than the complete
bagging ensembles. The performance of pruned ensembles is analyzed by means of
the bias-variance decomposition of the error.}
}
@INPROCEEDINGS{martinez05comites,
author = {Gonzalo Mart{\'{\i}}nez-Mu{\~n}oz and Alberto Su{\'a}rez},
title = {Comit\'es de \'arboles {IGP}},
booktitle = {Actas del I simposio de inteligencia computacional},
year = {2005},
pages = {277--283},
publisher = {Thomson Press},
}
@INPROCEEDINGS{martinez04aggregation,
author = {Gonzalo Mart{\'{\i}}nez-Mu{\~n}oz and Alberto Su{\'a}rez},
title = {Aggregation Ordering in Bagging},
booktitle = {Proc. of the {IASTED} International Conference on Artificial Intelligence
and Applications},
year = {2004},
pages = {258--263},
publisher = {Acta Press}
}
@INPROCEEDINGS{martinez02using,
author = {Gonzalo Mart{\'{\i}}nez-Mu{\~n}oz and Alberto Su{\'a}rez},
title = {Using All Data to Generate Decision Tree Ensembles},
booktitle = {Proc. of {L}earning'02},
year = {2002},
pages = {181--186},
}