Dissecting the Winning Solution of the HiggsML Challenge

Gábor Melis
Proceedings of the NIPS 2014 Workshop on High-energy Physics and Machine Learning, PMLR 42:57-67, 2015.

Abstract

The recent Higgs Machine Learning Challenge pitted one of the largest crowds seen in machine learning contests against one another. In this paper, we present the winning solution and investigate the effect of extra features, the choice of neural network activation function, regularization and data set size. We demonstrate improved classification accuracy using a very similar network architecture on the permutation invariant MNIST benchmark. Furthermore, we advocate the use of a simple method that lies on the boundary between bagging and cross-validation to both estimate the generalization error and improve accuracy.

Cite this Paper

BibTeX
@InProceedings{pmlr-v42-meli14, title = {Dissecting the Winning Solution of the HiggsML Challenge}, author = {Melis, Gábor}, booktitle = {Proceedings of the NIPS 2014 Workshop on High-energy Physics and Machine Learning}, pages = {57--67}, year = {2015}, editor = {Cowan, Glen and Germain, Cécile and Guyon, Isabelle and Kégl, Balázs and Rousseau, David}, volume = {42}, series = {Proceedings of Machine Learning Research}, address = {Montreal, Canada}, month = {13 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v42/meli14.pdf}, url = {https://proceedings.mlr.press/v42/meli14.html}, abstract = {The recent Higgs Machine Learning Challenge pitted one of the largest crowds seen in machine learning contests against one another. In this paper, we present the winning solution and investigate the effect of extra features, the choice of neural network activation function, regularization and data set size. We demonstrate improved classification accuracy using a very similar network architecture on the permutation invariant MNIST benchmark. Furthermore, we advocate the use of a simple method that lies on the boundary between bagging and cross-validation to both estimate the generalization error and improve accuracy.} }
Endnote
%0 Conference Paper %T Dissecting the Winning Solution of the HiggsML Challenge %A Gábor Melis %B Proceedings of the NIPS 2014 Workshop on High-energy Physics and Machine Learning %C Proceedings of Machine Learning Research %D 2015 %E Glen Cowan %E Cécile Germain %E Isabelle Guyon %E Balázs Kégl %E David Rousseau %F pmlr-v42-meli14 %I PMLR %P 57--67 %U https://proceedings.mlr.press/v42/meli14.html %V 42 %X The recent Higgs Machine Learning Challenge pitted one of the largest crowds seen in machine learning contests against one another. In this paper, we present the winning solution and investigate the effect of extra features, the choice of neural network activation function, regularization and data set size. We demonstrate improved classification accuracy using a very similar network architecture on the permutation invariant MNIST benchmark. Furthermore, we advocate the use of a simple method that lies on the boundary between bagging and cross-validation to both estimate the generalization error and improve accuracy.
RIS
TY - CPAPER TI - Dissecting the Winning Solution of the HiggsML Challenge AU - Gábor Melis BT - Proceedings of the NIPS 2014 Workshop on High-energy Physics and Machine Learning DA - 2015/08/27 ED - Glen Cowan ED - Cécile Germain ED - Isabelle Guyon ED - Balázs Kégl ED - David Rousseau ID - pmlr-v42-meli14 PB - PMLR DP - Proceedings of Machine Learning Research VL - 42 SP - 57 EP - 67 L1 - http://proceedings.mlr.press/v42/meli14.pdf UR - https://proceedings.mlr.press/v42/meli14.html AB - The recent Higgs Machine Learning Challenge pitted one of the largest crowds seen in machine learning contests against one another. In this paper, we present the winning solution and investigate the effect of extra features, the choice of neural network activation function, regularization and data set size. We demonstrate improved classification accuracy using a very similar network architecture on the permutation invariant MNIST benchmark. Furthermore, we advocate the use of a simple method that lies on the boundary between bagging and cross-validation to both estimate the generalization error and improve accuracy. ER -
APA
Melis, G.. (2015). Dissecting the Winning Solution of the HiggsML Challenge. Proceedings of the NIPS 2014 Workshop on High-energy Physics and Machine Learning, in Proceedings of Machine Learning Research 42:57-67 Available from https://proceedings.mlr.press/v42/meli14.html.

Related Material