Speaker
Description
In this talk we discuss a recent search over the parameter space of the Next-to-Minimal Supersymmetric Standard Model using deep learning techniques. The particular focus of this search is identifying parameter values that explain hints of excesses around 95 GeV and 650 GeV in Higgs studies, and a discrepancy in Electro-Weakino searches, as well as predicting mono-H and mono-Z signatures of dark matter. For this study we employ a recent scanning tool called DLScanner. This tool uses deep learning techniques to efficiently identify parameter regions that accommodate a number of constraints consistent with current observations as well as the mentioned scalars and Electro-Weakino. Furthermore, we present evidence of parameter values with promising possibilities for phenomenological studies.
This talk is based on "Explaining data excesses over the NMSSM parameter space with Deep Learning techniques" (JHEP 02 (2026) 077) by A. Hammad, Raymundo Ramos, Amit Chakraborty, Pyungwon Ko, and Stefano Moretti.