The Tracking Machine Learning Challenge: Throughput Phase

Abstract

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 $$O(10^5)$$ O ( 10 5 ) points, the participants had to connect them into $$O(10^4)$$ O ( 10 4 ) 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 is analysed in depth and lessons derived.

Potentiality of automatic parameter tuning suite available in ACTS track reconstruction software framework

“…A Common Tracking Software (ACTS) [1] is a tracking framework being developed since 2016 as an international collaboration with the goal of providing a generic, experimentindependent open-source software framework for charged particle tracks reconstruction. To facilitate comprehensive research, ACTS offers two simulated detector geometries: the Generic Detector as shown in figure 1 is a standard all-silicon LHC-type tracking detector used in the TrackML [2] challenge and the Open Data Detector (ODD) [3], an evolved version of Generic Detector implemented using DD4Hep [4] that provides the support structure and the material akin to a real detector. The Generic detector has been used for the seeding and vertexing optimization studies while ODD has been used for the material mapping studies in this paper.…”

An Object Condensation Pipeline for Charged Particle Tracking at the High Luminosity LHC

“…This study is performed using the TrackML dataset [4,5] that simulates the worst-case HL-LHC pileup conditions (⟨µ⟩ = 200) in a generic tracking detector geometry 1 . Our studies are limited to the innermost pixel detector layers, including 4 barrel layers and 7 layers in each endcap.…”

Accelerating progress in the social sciences: the potential of benchmarks

“…This was done in the hope of finding novel, high performing, and fast methods that could boost the field. The challenge was divided into two parts, an accuracy part in which the performance accuracy of the submitted algorithms was assessed (Amrouche et al, 2020), and a throughput part in which the speed of the methods was evaluated (Amrouche et al, 2023). The accuracy phase resulted in the submission of many ML methods, which were considered highly innovative in the field (Amrouche et al, 2020).…”

“…The accuracy phase resulted in the submission of many ML methods, which were considered highly innovative in the field (Amrouche et al, 2020). In the throughput phase, the three top-ranked submissions in terms of speed were shown to be considerably faster than the state-of-the-art algorithms in the field at the time (Amrouche et al, 2023).…”

“…The use of benchmarks has touched many fields of science including computer and data science (Bennett, 2007;Russakovsky et al, 2013), physics (Amrouche et al, 2020(Amrouche et al, , 2023, biomedicine (Antonelli et al, 2022), and the humanities (Candela et al, 2021;Papadimos et al, 2023;Larson et al, 2017). Traditionally, participants are invited to submit their models to the benchmark, which is commonly referred to as "organizing a challenge".…”