Universal New Physics Latent Space

TL;DR

This paper introduces a machine learning approach to map Standard Model and beyond Standard Model physics data into a unified latent space, enabling effective clustering and discrimination of different new physics models at the LHC.

Contribution

The authors develop a novel latent space mapping technique that preserves relationships between theories, facilitating model discrimination and coverage analysis in high-energy physics.

Findings

Models cluster according to their LHC phenomenology in latent space

Indistinguishable models are mapped to the same region

Method enables identification of gaps in model coverage

Abstract

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.