Speaker
Description
A transformation of collision data into new data structures that are suitable for machine learning techniques is an importation direction for future research. This study shows the usability of rapidity-mass matrices (RMM) for general event classification and for anomaly detection in collision data. The proposed standardization of the input feature space can simplify searches for signatures of new physics at the LHC when using machine learning techniques. In particular, using Monte Carlo simulations, we illustrate how to improve signal-over-background ratios in searches for new physics, how to filter out Standard Model events for model-agnostic searches. Some ideas related to anomaly detection in collision data are discussed. This work is based on https://arxiv.org/abs/1810.06669 (Universe (2021) 7(1), 19)
| Preferred track | Collectivity & Multiple Scattering |
|---|
