Combination of Conformal Predictors for Classification

Paolo Toccaceli, Alexander Gammerman
Proceedings of the Sixth Workshop on Conformal and Probabilistic Prediction and Applications, PMLR 60:39-61, 2017.

Abstract

The paper presents some possible approaches to the combination of Conformal Predictors in the binary classification case. A first class of methods is based on p-value combination techniques that have been proposed in the context of Statistical Hypothesis Testing; a second class is based on the calibration of p-values into Bayes factors. A few methods from these two classes are applied to a real-world case, namely the chemoinformatics problem of Compound Activity Prediction. Their performance is discussed, showing the different abilities to preserve of validity and improve efficiency. The experiments show that P-value combination, in particular Fisher’s method, can be advantageous when ranking compounds by strength of evidence.

Cite this Paper

BibTeX
@InProceedings{pmlr-v60-toccaceli17a, title = {Combination of Conformal Predictors for Classification}, author = {Toccaceli, Paolo and Gammerman, Alexander}, booktitle = {Proceedings of the Sixth Workshop on Conformal and Probabilistic Prediction and Applications}, pages = {39--61}, year = {2017}, editor = {Gammerman, Alex and Vovk, Vladimir and Luo, Zhiyuan and Papadopoulos, Harris}, volume = {60}, series = {Proceedings of Machine Learning Research}, month = {13--16 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v60/toccaceli17a/toccaceli17a.pdf}, url = {https://proceedings.mlr.press/v60/toccaceli17a.html}, abstract = {The paper presents some possible approaches to the combination of Conformal Predictors in the binary classification case. A first class of methods is based on p-value combination techniques that have been proposed in the context of Statistical Hypothesis Testing; a second class is based on the calibration of p-values into Bayes factors. A few methods from these two classes are applied to a real-world case, namely the chemoinformatics problem of Compound Activity Prediction. Their performance is discussed, showing the different abilities to preserve of validity and improve efficiency. The experiments show that P-value combination, in particular Fisher’s method, can be advantageous when ranking compounds by strength of evidence.} }
Endnote
%0 Conference Paper %T Combination of Conformal Predictors for Classification %A Paolo Toccaceli %A Alexander Gammerman %B Proceedings of the Sixth Workshop on Conformal and Probabilistic Prediction and Applications %C Proceedings of Machine Learning Research %D 2017 %E Alex Gammerman %E Vladimir Vovk %E Zhiyuan Luo %E Harris Papadopoulos %F pmlr-v60-toccaceli17a %I PMLR %P 39--61 %U https://proceedings.mlr.press/v60/toccaceli17a.html %V 60 %X The paper presents some possible approaches to the combination of Conformal Predictors in the binary classification case. A first class of methods is based on p-value combination techniques that have been proposed in the context of Statistical Hypothesis Testing; a second class is based on the calibration of p-values into Bayes factors. A few methods from these two classes are applied to a real-world case, namely the chemoinformatics problem of Compound Activity Prediction. Their performance is discussed, showing the different abilities to preserve of validity and improve efficiency. The experiments show that P-value combination, in particular Fisher’s method, can be advantageous when ranking compounds by strength of evidence.
APA
Toccaceli, P. & Gammerman, A.. (2017). Combination of Conformal Predictors for Classification. Proceedings of the Sixth Workshop on Conformal and Probabilistic Prediction and Applications, in Proceedings of Machine Learning Research 60:39-61 Available from https://proceedings.mlr.press/v60/toccaceli17a.html.

Related Material