Universal New Physics Latent Space
This work addresses model discrimination and benchmark selection for physicists analyzing LHC data, though it appears incremental as it builds on existing latent space techniques.
The authors tackled the problem of distinguishing between Standard Model and various beyond-the-Standard-Model theories in LHC data by developing a machine learning method that maps them into a unified latent space, showing that models cluster distinctly based on their phenomenology.
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.