Conveners
ML+computing Parallel: ML+computing Parallel
- Marcel Rieger (UNI/EXP (Uni Hamburg, Institut fur Experimentalphysik))
- Stephen Jiggins (ATLAS (ATLAS-Experiment))
In order to observe and measure rare processes in nature, a staggering amount of data needs to be produced and processed at particle colliders. With the advancement of the LHC towards Run 3 and HL-LHC, the flow of data as well as the complexity of the analyses will increase even more. In light of these challenges and the limited resources available, an efficient usage of computing power is...
Future collider experiments, such as the upcoming high luminosity phase of the LHC, are expected to be extremely data-rich. This anticipates a significant demand for innovative track reconstruction techniques to more efficiently reconstruct particle trajectories. Specifically, LUXE (Laser Und XFEL Experiment) at DESY, a proposed experiment to investigate the transition into strong-field QED,...
Particle track reconstruction plays a crucial role in the exploration of new physical phenomena, particularly when rare signal tracks are obscured by a significant background. In muon colliders where beam muons interacting with the detector produce secondary and tertiary background particles, track reconstruction can be computationally intensive due to the large number of detector hits. The...
In a wide range of high-energy particle physics analyses, machine learning methods have proven as powerful tools to enhance analysis sensitivity.
In the past years, various machine learning applications were also integrated in central CMS workflows, leading to great improvements in reconstruction and object identification efficiencies.
However, the continuation of successful deployments...
In a quantum mechanical process, perturbative calculations, such as in proton-proton collisions at the LHC, can introduce negative density terms as the perturbative series increases to higher order. Consequently, numerical sampling techniques (e.g. Monte Carlo) result in data points with either positive or negative weights. This is an issue for probabilistic machine learning-based algorithms...
