ν-Flows: Conditional Neutrino Regression
This addresses the challenge of neutrino momentum reconstruction in particle physics experiments, offering a domain-specific improvement for high-energy collider data analysis.
The paper tackled the problem of reconstructing neutrino kinematics in high-energy collider experiments, which is typically left as a free parameter, by introducing ν-Flows, a method using conditional normalizing flows and deep invertible neural networks; the result showed more accurate momentum reconstruction, especially for the longitudinal coordinate, and improved jet association by up to a factor of 1.41 compared to conventional methods.
We present $ν$-Flows, a novel method for restricting the likelihood space of neutrino kinematics in high energy collider experiments using conditional normalizing flows and deep invertible neural networks. This method allows the recovery of the full neutrino momentum which is usually left as a free parameter and permits one to sample neutrino values under a learned conditional likelihood given event observations. We demonstrate the success of $ν$-Flows in a case study by applying it to simulated semileptonic $t\bar{t}$ events and show that it can lead to more accurate momentum reconstruction, particularly of the longitudinal coordinate. We also show that this has direct benefits in a downstream task of jet association, leading to an improvement of up to a factor of 1.41 compared to conventional methods.