The matrix element method is the LHC inference method of choice for limited statistics. We present a dedicated machine learning framework, based on efficient phase-space integration, a learned acceptance and transfer function. It is based on a choice of INN and diffusion networks, and a transformer to solve jet combinatorics. We showcase this setup for the CP-phase of the top Yukawa coupling in associated Higgs and single-top production.
@article{arxiv.2310.07752,
title = {Precision-Machine Learning for the Matrix Element Method},
author = {Theo Heimel and Nathan Huetsch and Ramon Winterhalder and Tilman Plehn and Anja Butter},
journal= {arXiv preprint arXiv:2310.07752},
year = {2024}
}
Comments
26 pages, 12 figures, v2: update references, v3: include evaluation on Herwig