Logo Logo
Hilfe
Hilfe
Switch Language to English

Abudinen, F.; Bertemes, M.; Bilokin, S.; Campajola, M.; Casarosa, G.; Cunliffe, S.; Corona, L.; De Nuccio, M.; De Pietro, G.; Dey, S.; Eliachevitch, M.; Feichtinger, P.; Ferber, T.; Gemmler, J.; Goldenzweig, P.; Gottmann, A.; Graziani, E.; Haigh, H.; Hohmann, M.; Humair, T.; Inguglia, G.; Kahn, J.; Keck, T.; Komarov, I.; Krohn, J.-F.; Kuhr, T.; Lacaprara, S.; Lieret, K.; Maiti, R.; Martini, A.; Meier, F.; Metzner, F.; Milesi, M.; Park, S.-H.; Prim, M.; Pulvermacher, C.; Ritter, M.; Sato, Y.; Schwanda, C.; Sutcliffe, W.; Tamponi, U.; Tenchini, F.; Urquijo, P.; Zani, L.; Zlebcik, R. und Zupanc, A. (2022): Punzi-loss: a non-differentiable metric approximation for sensitivity optimisation in the search for new particles. In: European Physical Journal C : Particles and Fields, Bd. 82, Nr. 2, 121

Volltext auf 'Open Access LMU' nicht verfügbar.

Abstract

We present the novel implementation of a non-differentiable metric approximation and a corresponding loss-scheduling aimed at the search for new particles of unknown mass in high energy physics experiments. We call the loss-scheduling, based on the minimisation of a figure-of-merit related function typical of particle physics, a Punzi-loss function, and the neural network that utilises this loss function a Punzi-net. We show that the Punzi-net outperforms standard multivariate analysis techniques and generalises well to mass hypotheses for which it was not trained. This is achieved by training a single classifier that provides a coherent and optimal classification of all signal hypotheses over the whole search space. Our result constitutes a complementary approach to fully differentiable analyses in particle physics. We implemented this work using PyTorch and provide users full access to a public repository containing all the codes and a training example.

Dokument bearbeiten Dokument bearbeiten