Machine Learning wins the Higgs Challenge
The winner of the four-month-long Higgs Machine Learning Challenge, launched on 12 May, is Gábor Melis from Hungary, followed closely by Tim Salimans from the Netherlands and Pierre Courtiol from France. The challenge explored the potential of advanced machine learning methods to improve the significance of the Higgs discovery.
Winners of the Higgs Machine Learning Challenge: Gábor Melis and Tim Salimans (top row), Tianqi Chen and Tong He (bottom row).
Participants in the Higgs Machine Learning Challenge were tasked with developing an algorithm to improve the detection of Higgs boson signal events decaying into two tau particles in a sample of simulated ATLAS data* that contains few signal and a majority of non-Higgs boson “background” events. No knowledge of particle physics was required for the challenge but skills in machine learning - the training of computers to recognise patterns in data – were essential. The Challenge, hosted by Kaggle, had an all-time record of 1,785 teams participating.
“The huge success of the challenge shows the fascination that the discovery of the Higgs boson, including the statistical tools used for it, holds for the public,” says Andreas Hoecker, physics coordinator of the ATLAS experiment. "It also reveals that experimental particle physics, in spite of its sophistication, can learn a lot from machine learning science."
Winner Gábor Melis, a graduate in software engineering and mathematics, developed an algorithm that is an ensemble of deep neural networks trained on random subsets of data provided with very little feature engineering and no physics knowledge. Meanwhile, runner-up Tim Salimans, who has a PhD in Econometrics and works as a data science consultant, developed a solution he describes as a combination of a large number of boosted decision tree ensembles, with some tricks to improve statistical efficiency.
In addition to the main winners, the Special High Energy Physics meets Machine Learning Award has been presented to Tianqi Chen and Tong He of Team Crowwork. Though their score was 3.72 to Melis’ 3.81, a thorough scrutiny showed that Crowwork’s XG Boost algorithm was an excellent compromise between performance and simplicity, which could improve tools currently used in high-energy physics. The team has been invited to CERN next year for a workshop where they will discuss the application of machine learning techniques in high-energy physics.
* The simulated data used for the challenge will be made available on opendata.cern.ch for those who would like to test new ideas.
