TY  - JOUR
PB  - SciPost Foundation
DO  - 10.21468/SciPostPhys.14.6.159
TI  - $\nu$-flows: Conditional neutrino regression
PY  - 2023/06/16
UR  - https://www.scipost.org/SciPostPhys.14.6.159
JF  - SciPost Physics
JA  - SciPost Phys.
VL  - 14
IS  - 6
SP  - 159
A1  - Leigh, Matthew
AU  - Raine, John Andrew
AU  - Zoch, Knut
AU  - Golling, Tobias
AB  - We present $\nu$-Flows, a novel method for restricting the likelihood space of neutrino kinematics in high-energy collider experiments using conditional normalising 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 $\nu$-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.
ER  -

@Article{10.21468/SciPostPhys.14.6.159,
	title={{$\nu$-flows: Conditional neutrino regression}},
	author={Matthew Leigh and John Andrew Raine and Knut Zoch and Tobias Golling},
	journal={SciPost Phys.},
	volume={14},
	pages={159},
	year={2023},
	publisher={SciPost},
	doi={10.21468/SciPostPhys.14.6.159},
	url={https://scipost.org/10.21468/SciPostPhys.14.6.159},
}