Pileup Mitigation with Machine Learning (PUMML)
This addresses a critical issue in high-energy physics experiments for researchers, offering a novel data-driven approach to improve measurement accuracy.
The paper tackles the problem of pileup contamination in particle physics by developing a machine learning technique using convolutional neural networks to isolate the energy distribution of particles from the primary collision, achieving significant reduction in distortion across various jet observables.
Pileup involves the contamination of the energy distribution arising from the primary collision of interest (leading vertex) by radiation from soft collisions (pileup). We develop a new technique for removing this contamination using machine learning and convolutional neural networks. The network takes as input the energy distribution of charged leading vertex particles, charged pileup particles, and all neutral particles and outputs the energy distribution of particles coming from leading vertex alone. The PUMML algorithm performs remarkably well at eliminating pileup distortion on a wide range of simple and complex jet observables. We test the robustness of the algorithm in a number of ways and discuss how the network can be trained directly on data.