Learning New Physics from Data -- a Symmetrized Approach

Thousands of person-years have been invested in searches for New Physics (NP), the majority of them motivated by theoretical considerations. Yet, no evidence of beyond the Standard Model (BSM) physics has been found. This suggests that model-agnostic searches might be an important key to explore NP, and help discover unexpected phenomena which can inspire future theoretical developments. A possible strategy for such searches is identifying asymmetries between data samples that are expected to be symmetric within the Standard Model (SM). We propose exploiting neural networks (NNs) to quickly fit and statistically test the differences between two samples. Our method is based on an earlier work, originally designed for inferring the deviations of an observed dataset from that of a much larger reference dataset. We present a symmetric formalism, generalizing the original one; avoiding fine-tuning of the NN parameters and any constraints on the relative sizes of the samples. Our formalism could be used to detect small symmetry violations, extending the discovery potential of current and future particle physics experiments.