CERN Accelerating science

Article
Report number	arXiv:1904.06778
Title	The Tracking Machine Learning challenge : Accuracy phase
Author(s)	Amrouche, Sabrina (Geneva U.) ; Basara, Laurent (LRI, Paris 11) ; Calafiura, Paolo (LBL, Berkeley) ; Estrade, Victor (LRI, Paris 11) ; Farrell, Steven (LBL, Berkeley) ; Ferreira, Diogo R. (Lisbon, IST) ; Finnie, Liam (IBM, Boblingen) ; Finnie, Nicole (CFEL, Hamburg) ; Germain, Cécile (LRI, Paris 11) ; Gligorov, Vladimir Vava (Paris U., VI-VII) ; Golling, Tobias (Geneva U.) ; Gorbunov, Sergey (Goethe U., Frankfurt (main)) ; Gray, Heather (LBL, Berkeley) ; Guyon, Isabelle (INRIA, Saclay) ; Hushchyn, Mikhail (Yandex Sch. Data Anal., Moscow ; Higher Sch. of Economics, Moscow) ; Innocente, Vincenzo (CERN) ; Kiehn, Moritz (Geneva U.) ; Moyse, Edward (Massachusetts U., Amherst) ; Puget, Jean-Francois (IBM Watson Res. Ctr.) ; Reina, Yuval (Unlisted, IL) ; Rousseau, David (Orsay, LAL) ; Salzburger, Andreas (CERN) ; Ustyuzhanin, Andrey (Yandex Sch. Data Anal., Moscow ; Higher Sch. of Economics, Moscow) ; Vlimant, Jean-Roch (Caltech) ; Wind, Johan Sokrates (Oslo U.) ; Xylouris, Trian (Unlisted, DE) ; Yilmaz, Yetkin (Orsay, LAL)
Publication	2020
Imprint	2019-04-14
Number of pages	36
Note	36 pages, 22 figures
Published in:	10.1007/978-3-030-29135-8_9
Presented at	32nd Annual Conference on Neural Information Processing Systems (NeurIPS 2018), Montréal, Canada, 2 - 8 Dec 2018, pp.231-264
DOI	10.1007/978-3-030-29135-8_9
Subject category	physics.data-an ; Other Fields of Physics ; hep-ex ; Particle Physics - Experiment
Abstract	This paper reports the results of an experiment in high energy physics: using the power of the "crowd" to solve difficult experimental problems linked to tracking accurately the trajectory of particles in the Large Hadron Collider (LHC). This experiment took the form of a machine learning challenge organized in 2018: the Tracking Machine Learning Challenge (TrackML). Its results were discussed at the competition session at the Neural Information Processing Systems conference (NeurIPS 2018). Given 100.000 points, the participants had to connect them into about 10.000 arcs of circles, following the trajectory of particles issued from very high energy proton collisions. The competition was difficult with a dozen front-runners well ahead of a pack. The single competition score is shown to be accurate and effective in selecting the best algorithms from the domain point of view. The competition has exposed a diversity of approaches, with various roles for Machine Learning, a number of which are discussed in the document
Other source	Inspire
Copyright/License	publication: © 2020-2024 Springer Nature Switzerland preprint: (License: arXiv nonexclusive-distrib 1.0)