Truth, beauty, and goodness in grand unification: a machine learning approach
This addresses a specific issue in theoretical particle physics for researchers in GUT models, but it is incremental as it compares existing approaches.
The paper tackled the problem of predicting fermion masses in the minimal supersymmetric SU(5) Grand Unified Theory, which disagrees with observed values, by comparing two approaches using machine learning optimization, finding that the 24-Higgs approach achieves observed masses with smaller modifications.
We investigate the flavour sector of the supersymmetric $SU(5)$ Grand Unified Theory (GUT) model using machine learning techniques. The minimal $SU(5)$ model is known to predict fermion masses that disagree with observed values in nature. There are two well-known approaches to address this issue: one involves introducing a 45-representation Higgs field, while the other employs a higher-dimensional operator involving the 24-representation GUT Higgs field. We compare these two approaches by numerically optimising a loss function, defined as the ratio of determinants of mass matrices. Our findings indicate that the 24-Higgs approach achieves the observed fermion masses with smaller modifications to the original minimal $SU(5)$ model.