The Higgs boson machine learning challenge

Claire Adam-Bourdarios (1) , Glen Cowan (2) , Cécile Germain (3, 4, 5) , Isabelle Guyon (6) , Balázs Kégl (3, 1, 5) , David Rousseau (1)

1 LAL - Laboratoire de l'Accélérateur Linéaire
2 Department of Physics [Egham]
3 TAO - Machine Learning and Optimisation
4 UP11 - Université Paris-Sud - Paris 11
5 LRI - Laboratoire de Recherche en Informatique
6 Chalearn

The Higgs Boson Machine Learning Challenge (HiggsML or the Challenge for short) was organized to promote collaboration between high energy physicists and data scientists. The ATLAS experiment at CERN provided simulated data that has been used by physi- cists in a search for the Higgs boson. The Challenge was organized by a small group of ATLAS physicists and data scientists. It was hosted by Kaggle at https://www.kaggle. com/c/higgs-boson; the challenge data is now available on http://opendata.cern.ch/ collection/ATLAS-Higgs-Challenge-2014. This paper provides the physics background and explains the challenge setting, the challenge design, and analyzes its results.

Mots clés: high energy physics; Higgs boson; statistical tests; machine learning

Domaines: Intelligence artificielle [cs.AI]; Physique des Hautes Energies - Expérience [hep-ex]; Calcul parallèle, distribué et partagé [cs.DC]

Claire Adam-Bourdarios, Glen Cowan, Cécile Germain, Isabelle Guyon, Balázs Kégl, et al.. The Higgs boson machine learning challenge. NIPS 2014 Workshop on High-energy Physics and Machine Learning, Dec 2014, Montreal, Canada. pp.37. ⟨hal-01208587⟩