Universal new physics latent space
We develop a machine learning method for mapping data originating from both Standard Model processes and various theories beyond the Standard Model into a unified representation (latent) space while conserving information about the relationship between the underlying theories. We apply our method to three examples of new physics at the LHC of increasing complexity, showing that models can be clustered according to their LHC phenomenology: different models are mapped to distinct regions in latent space, while indistinguishable models are mapped to the same region. This opens interesting new avenues on several fronts, such as model discrimination, selection of representative benchmark scenarios, and identifying gaps in the coverage of model space.
Authors
- Anna Hallin (ORCID: https://orcid.org/0000-0002-1551-814X)
- Gregor Kasieczka (ORCID: https://orcid.org/0000-0003-3457-2755)
- André Lessa (ORCID: https://orcid.org/0000-0002-5251-7891)
- David Shih (ORCID: https://orcid.org/0000-0003-3408-3871)
- Sabine Kraml (ORCID: https://orcid.org/0000-0002-2613-7000)
- L. Moureaux (ORCID: https://orcid.org/0000-0002-2310-9266)
- Tore von Schwartz
Institutions
- Universität Hamburg (DE)
- Rutgers Sexual and Reproductive Health and Rights (NL)
- Laboratoire de Physique Subatomique et de Cosmologie (FR)
- Universidade Federal do ABC (BR)
- Université Grenoble Alpes (FR)
Publication Details
- Journal
- Physical review. D/Physical review. D.
- Published
- 2025-01-09
- DOI
- https://doi.org/10.1103/physrevd.111.016006
- Primary Topic
- Particle physics theoretical and experimental studies
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Science Foundation
- U.S. Department of Energy
- Aspen Center for Physics
- Deutsche Forschungsgemeinschaft
- Fundação de Amparo à Pesquisa do Estado de São Paulo
- Deutsches Elektronen-Synchrotron