skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

This content will become publicly available on November 30, 2020

Title: The Tracking Machine Learning Challenge: Accuracy Phase

Abstract

This work 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

Authors:
 [1];  [2];  [3];  [2];  [3];  [4];  [5];  [6];  [2];  [7];  [1];  [8];  [3];  [9];  [10];  [11];  [1];  [12];  [13];  [14] more »;  [15];  [11];  [10];  [16];  [17];  [18];  [15] « less
  1. Univ. of Geneva (Switzerland)
  2. Univ. Paris-Saclay, Gif-sur-Yvette (France)
  3. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
  4. Univ. of Lisbon (Portugal)
  5. IBM Germany Research and Development (Germany)
  6. Bosch Center for Artificial Intelligence (Germany)
  7. Sorbonne Univ., Paris (France)
  8. Goethe Univ., Frankfurt (Germany)
  9. Univ. Paris-Saclay, Orsay (France); ChaLearn, Berkeley, CA (United States)
  10. National Research Univ. Higher School of Economics, Moscow (Russia); Yandex School of Data Analysis, Moscow (Russia)
  11. European Organization for Nuclear Research (CERN), Geneva (Switzerland)
  12. Univ. of Massachusetts, Amherst, MA (United States)
  13. IBM France Lab, Biot (France). Data and AI R&D
  14. Tel-Aviv (Israel)
  15. Univ. Paris-Sud, Orsay (France); Univ. Paris-Saclay, Orsay (France)
  16. California Inst. of Technology (CalTech), Pasadena, CA (United States)
  17. Norwegian Univ. of Science and Technology, Oslo (Norway)
  18. Frankfurt am Main (Germany)
Publication Date:
Research Org.:
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
Sponsoring Org.:
USDOE Office of Science (SC); Swiss National Science Foundation (SNF); German Federal Ministry of Education and Research (BMBF); European Union Horizon 2020
Contributing Org.:
[Kaggle; Nvidia; Université de Genève; Chalearn; ERC mPP; DataIA; CERN Openlab; Paris-Saclay CDS; INRIA; ERC RECEPT; Common Ground; Université Paris Sud; INQNET; Fermilab; pyTorch]
OSTI Identifier:
1603580
Report Number(s):
[arXiv:1904.06778v2]
[ ark:/13030/qt4rk7395g]
Grant/Contract Number:  
[AC02-05CH11231; 200020_181984; 724777; 772369; 654168]
Resource Type:
Accepted Manuscript
Country of Publication:
United States
Language:
English

Citation Formats

Amrouche, Sabrina, Basara, Laurent, Calafiura, Paolo, Estrade, Victor, Farrell, Steven, Ferreira, Diogo R., Finnie, Liam, Finnie, Nicole, Germain, Cécile, Gligorov, Vladimir Vava, Golling, Tobias, Gorbunov, Sergey, Gray, Heather, Guyon, Isabelle, Hushchyn, Mikhail, Innocente, Vincenzo, Kiehn, Moritz, Moyse, Edward, Puget, Jean-François, Reina, Yuval, Rousseau, David, Salzburger, Andreas, Ustyuzhanin, Andrey, Vlimant, Jean-Roch, Wind, Johan Sokrates, Xylouris, Trian, and Yilmaz, Yetkin. The Tracking Machine Learning Challenge: Accuracy Phase. United States: N. p., 2019. Web. doi:10.1007/978-3-030-29135-8_9.
Amrouche, Sabrina, Basara, Laurent, Calafiura, Paolo, Estrade, Victor, Farrell, Steven, Ferreira, Diogo R., Finnie, Liam, Finnie, Nicole, Germain, Cécile, Gligorov, Vladimir Vava, Golling, Tobias, Gorbunov, Sergey, Gray, Heather, Guyon, Isabelle, Hushchyn, Mikhail, Innocente, Vincenzo, Kiehn, Moritz, Moyse, Edward, Puget, Jean-François, Reina, Yuval, Rousseau, David, Salzburger, Andreas, Ustyuzhanin, Andrey, Vlimant, Jean-Roch, Wind, Johan Sokrates, Xylouris, Trian, & Yilmaz, Yetkin. The Tracking Machine Learning Challenge: Accuracy Phase. United States. doi:10.1007/978-3-030-29135-8_9.
Amrouche, Sabrina, Basara, Laurent, Calafiura, Paolo, Estrade, Victor, Farrell, Steven, Ferreira, Diogo R., Finnie, Liam, Finnie, Nicole, Germain, Cécile, Gligorov, Vladimir Vava, Golling, Tobias, Gorbunov, Sergey, Gray, Heather, Guyon, Isabelle, Hushchyn, Mikhail, Innocente, Vincenzo, Kiehn, Moritz, Moyse, Edward, Puget, Jean-François, Reina, Yuval, Rousseau, David, Salzburger, Andreas, Ustyuzhanin, Andrey, Vlimant, Jean-Roch, Wind, Johan Sokrates, Xylouris, Trian, and Yilmaz, Yetkin. Sat . "The Tracking Machine Learning Challenge: Accuracy Phase". United States. doi:10.1007/978-3-030-29135-8_9.
@article{osti_1603580,
title = {The Tracking Machine Learning Challenge: Accuracy Phase},
author = {Amrouche, Sabrina and Basara, Laurent and Calafiura, Paolo and Estrade, Victor and Farrell, Steven and Ferreira, Diogo R. and Finnie, Liam and Finnie, Nicole and Germain, Cécile and Gligorov, Vladimir Vava and Golling, Tobias and Gorbunov, Sergey and Gray, Heather and Guyon, Isabelle and Hushchyn, Mikhail and Innocente, Vincenzo and Kiehn, Moritz and Moyse, Edward and Puget, Jean-François and Reina, Yuval and Rousseau, David and Salzburger, Andreas and Ustyuzhanin, Andrey and Vlimant, Jean-Roch and Wind, Johan Sokrates and Xylouris, Trian and Yilmaz, Yetkin},
abstractNote = {This work 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},
doi = {10.1007/978-3-030-29135-8_9},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2019},
month = {11}
}

Journal Article:
Free Publicly Available Full Text
This content will become publicly available on November 30, 2020
Publisher's Version of Record

Save / Share:

Works referenced in this record:

Long Short-Term Memory
journal, November 1997


L1 track triggering with associative memory for the CMS HL-LHC tracker
journal, November 2014


Multidimensional binary search trees used for associative searching
journal, September 1975


The HEP.TrkX Project: deep neural networks for HL-LHC online and offline tracking
journal, January 2017


Comparing clusterings—an information based distance
journal, May 2007


Objective Criteria for the Evaluation of Clustering Methods
journal, December 1971


IPython: A System for Interactive Scientific Computing
journal, January 2007

  • Perez, Fernando; Granger, Brian E.
  • Computing in Science & Engineering, Vol. 9, Issue 3
  • DOI: 10.1109/MCSE.2007.53

Track reconstruction at LHC as a collaborative data challenge use case with RAMP
journal, January 2017


Individual Comparisons by Ranking Methods
journal, December 1945

  • Wilcoxon, Frank
  • Biometrics Bulletin, Vol. 1, Issue 6
  • DOI: 10.2307/3001968

The ATLAS Simulation Infrastructure
journal, September 2010


A brief introduction to PYTHIA 8.1
journal, June 2008

  • Sjöstrand, Torbjörn; Mrenna, Stephen; Skands, Peter
  • Computer Physics Communications, Vol. 178, Issue 11
  • DOI: 10.1016/j.cpc.2008.01.036