Speaker
Description
For physics analyses with identical final state objects, e.g. jets, the correct sorting of the objects at the input of the analysis can lead to a considerable performance increase.
We present a new approach in which a sorting network is placed upstream of a classification network. The sorting network combines the whole event information and explicitly pre-sorts the inputs of the analysis. Because the optimal order is generally not known, a reinforcement learning approach is chosen, in which the sorting agent is trained with end-to-end feedback from the analysis environment. In this way, we enable the system to autonomously find an optimal solution. This new approach works for almost any analysis.
Using the example of top-quark pair associated Higgs boson production, we show an improvement of the signal and background separation in comparison to conventional sorting of jets with respect to their transverse momenta.
| Consider for promotion | No |
|---|
