Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

T: Fachverband Teilchenphysik

T 37: Search for New Particles II

T 37.4: Vortrag

Dienstag, 16. März 2021, 16:45–17:00, Tl

Machine Learning Based Dijet Anomaly Search — Lukas Judith, Gregor Kasieczka, •Tobias Lösche, and Manuel Sommerhalder — Institut für Experimentalphysik, Luruper Chaussee 149, 22761 Hamburg

The search for particles and phenomena beyond the Standard Model (BSM) is a crucial part of the current LHC physics program. Although considerable effort has been put into the investigation of BSM physics at the LHC as well as other experiments, no evidence has been found so far. A major disadvantage of many current searches is their reliance on specific signal and background models. Since it is not feasible to cover all possible BSM models with a dedicated search and the unexplored regions of the LHC phase space are vast, it is necessary to develop novel model-independent anomaly detection methods, which can be directly trained on and applied to data.

One proposed method for model-independent anomaly detection is ANODE. It uses density estimation based on normalizing flows to learn the densities in signal and background regions and has achieved state-of-the-art results in a recent community study. We present the first application of ANODE for a search for new physics with the CMS experiment in the dijet final state.