Dual perturb and combine algorithm

Pierre Geurts

Proceedings of the Eighth International Workshop on Artificial Intelligence and Statistics, PMLR R3:106-111, 2001.

Abstract

In this paper, a dual perturb and combine algorithm is proposed which consists in producing the perturbed predictions at the prediction stage using only one model. To this end, the attribute vector of a test case is perturbed several times by an additive random noise, the model is applied to each of these perturbed vectors and the resulting predictions are aggregated. An analytical version of this algorithm is described in the context of decision tree induction. From experiments on several datasets, it appears that this simple algorithm yields significant improvements on several problems, sometimes comparable to those obtained with bagging. When combined with decision tree bagging, this algorithm also improves accuracy in many problems.

Cite this Paper

BibTeX


@InProceedings{pmlr-vR3-geurts01a,
  title = 	 {Dual perturb and combine algorithm},
  author =       {Geurts, Pierre},
  booktitle = 	 {Proceedings of the Eighth International Workshop on Artificial Intelligence and Statistics},
  pages = 	 {106--111},
  year = 	 {2001},
  editor = 	 {Richardson, Thomas S. and Jaakkola, Tommi S.},
  volume = 	 {R3},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {04--07 Jan},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/r3/geurts01a/geurts01a.pdf},
  url = 	 {https://proceedings.mlr.press/r3/geurts01a.html},
  abstract = 	 {In this paper, a dual perturb and combine algorithm is proposed which consists in producing the perturbed predictions at the prediction stage using only one model. To this end, the attribute vector of a test case is perturbed several times by an additive random noise, the model is applied to each of these perturbed vectors and the resulting predictions are aggregated. An analytical version of this algorithm is described in the context of decision tree induction. From experiments on several datasets, it appears that this simple algorithm yields significant improvements on several problems, sometimes comparable to those obtained with bagging. When combined with decision tree bagging, this algorithm also improves accuracy in many problems.},
  note =         {Reissued by PMLR on 31 March 2021.}
}

Endnote

%0 Conference Paper
%T Dual perturb and combine algorithm
%A Pierre Geurts
%B Proceedings of the Eighth International Workshop on Artificial Intelligence and Statistics
%C Proceedings of Machine Learning Research
%D 2001
%E Thomas S. Richardson
%E Tommi S. Jaakkola	
%F pmlr-vR3-geurts01a
%I PMLR
%P 106--111
%U https://proceedings.mlr.press/r3/geurts01a.html
%V R3
%X In this paper, a dual perturb and combine algorithm is proposed which consists in producing the perturbed predictions at the prediction stage using only one model. To this end, the attribute vector of a test case is perturbed several times by an additive random noise, the model is applied to each of these perturbed vectors and the resulting predictions are aggregated. An analytical version of this algorithm is described in the context of decision tree induction. From experiments on several datasets, it appears that this simple algorithm yields significant improvements on several problems, sometimes comparable to those obtained with bagging. When combined with decision tree bagging, this algorithm also improves accuracy in many problems.
%Z Reissued by PMLR on 31 March 2021.

APA


Geurts, P.. (2001). Dual perturb and combine algorithm. Proceedings of the Eighth International Workshop on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research R3:106-111 Available from https://proceedings.mlr.press/r3/geurts01a.html. Reissued by PMLR on 31 March 2021.

Related Material

Download PDF