The Tracking Machine Learning challenge : Throughput phase - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue Computing and Software for Big Science Année : 2023

The Tracking Machine Learning challenge : Throughput phase

Laurent Basara
  • Fonction : Auteur
  • PersonId : 1092609
Dmitry Emeliyanov
  • Fonction : Auteur
  • PersonId : 1092611
Tobias Golling
  • Fonction : Auteur
  • PersonId : 1092613
Sergey Gorbunov
  • Fonction : Auteur
  • PersonId : 1092614
Heather Gray
  • Fonction : Auteur
  • PersonId : 1092615
Mikhail Hushchyn
  • Fonction : Auteur
  • PersonId : 1092616
Moritz Kiehn
  • Fonction : Auteur
  • PersonId : 1092618
Andrey Ustyuzhanin
  • Fonction : Auteur
  • PersonId : 1092621
Jean-Roch Vlimant
  • Fonction : Auteur
  • PersonId : 1092622

Résumé

This paper reports on the second "Throughput" phase of the Tracking Machine Learning (TrackML) challenge on the Codalab platform. As in the first "Accuracy" phase, the participants had to solve a difficult experimental problem linked to tracking accurately the trajectory of particles as e.g. created at the Large Hadron Collider (LHC): given (10^5) points, the participants had to connect them into (10^3) individual groups that represent the particle trajectories which are approximated helical. While in the first phase only the accuracy mattered, the goal of this second phase was a compromise between the accuracy and the speed of inference. Both were measured on the Codalab platform where the participants had to upload their software. The best three participants had solutions with good accuracy and speed an order of magnitude faster than the state of the art when the challenge was designed. Although the core algorithms were less diverse than in the first phase, a diversity of techniques have been used and are described in this paper. The performance of the algorithms are analysed in depth and lessons derived.
Fichier principal
Vignette du fichier
trackmlchapter.pdf (728.88 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03159824 , version 1 (04-03-2021)
hal-03159824 , version 2 (06-03-2021)

Identifiants

Citer

Sabrina Amrouche, Laurent Basara, Paolo Calafiura, Dmitry Emeliyanov, Victor Estrade, et al.. The Tracking Machine Learning challenge : Throughput phase. Computing and Software for Big Science, 2023, 7 (1), pp.1. ⟨10.1007/s41781-023-00094-w⟩. ⟨hal-03159824v2⟩
338 Consultations
145 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More