A method for inferring signal strength modifiers by conditional invertible neural networks

EPJ Web of Conferences, vol. 295, pp. 012080

Abstract

Abstract The continuous growth in model complexity in high-energy physics (HEP) collider experiments demands increasingly time-consuming model fits. We show first results on the application of conditional invertible networks (cINNs) to this challenge. Specifically, we construct and train a cINN to learn the mapping from signal strength modifiers to observables and its inverse. The resulting network infers the posterior distribution of the signal strength modifiers rapidly and for low computational cost. We present performance indicators of such a setup including the treatment of systematic uncertainties and highlight the features of cINNs estimating a signal strength for HEP-data on simulations.

Authors 4

1. M Farkas corresponding Aachen III. Physikalisches Institut A

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University, III. Physikalisches Institut A, Otto-Blumenthal-Straße, 52074 Aachen, Germany

2. S. Diekmann corresponding Aachen III. Physikalisches Institut A

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University, III. Physikalisches Institut A, Otto-Blumenthal-Straße, 52074 Aachen, Germany

3. N. Eich corresponding Aachen III. Physikalisches Institut A

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University, III. Physikalisches Institut A, Otto-Blumenthal-Straße, 52074 Aachen, Germany

4. Martin Erdmann corresponding Aachen III. Physikalisches Institut A

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University, III. Physikalisches Institut A, Otto-Blumenthal-Straße, 52074 Aachen, Germany