Precision-machine learning for the matrix element method
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.
Authors
- Theo Heimel (ORCID: https://orcid.org/0000-0002-3533-4591)
- Tilman Plehn (ORCID: https://orcid.org/0000-0001-5660-7790)
- Ramon Winterhalder (ORCID: https://orcid.org/0000-0002-9902-578X)
- Anja Butter
- Nathan Huetsch
Institutions
- Centre National de la Recherche Scientifique (FR)
- Université Paris Cité (FR)
- Heidelberg University (DE)
- Sorbonne Université (FR)
- Laboratoire de Physique Nucléaire et de Hautes Énergies (FR)
- Institut National de Physique Nucléaire et de Physique des Particules (FR)
- UCLouvain (BE)
Publication Details
- Journal
- SciPost Physics
- Published
- 2024-11-08
- DOI
- https://doi.org/10.21468/scipostphys.17.5.129
- Citations
- 19
- Primary Topic
- Particle physics theoretical and experimental studies
- Type
- article
- Field-Weighted Citation Impact
- 12.53
Funders
- Carl-Zeiss-Stiftung
- Baden-Württemberg Stiftung
- Deutsche Forschungsgemeinschaft
- Bundesministerium für Bildung und Forschung
- Fonds De La Recherche Scientifique - FNRS