Speaker
Description
The Matrix Element Method (MEM) is a well motivated multivariate technique to access the likelihood of a reconstructed event given a hypothesis. It offers optimal statistical power for hypothesis testing in particle physics, but it is limited by the computation of the intensive multi-dimensional integrals required to model detector and theory effects. We present a novel approach that addresses this challenge by employing Transformers and generative machine learning (ML) models. Specifically, we utilize ML surrogates to efficiently sample the phasespace for different physics processes and to accurately encode the complex transfer functions describing detector reconstruction. We demonstrate this technique on the challenging ttH(bb) process in the semileptonic channel using the full CMS detector simulation. This advancement enables precise measurements of Standard Model Effective Field Theory (EFT) couplings in a theoretical motivated way.
| Presentation type. | Talk |
|---|