Search papers, labs, and topics across Lattice.
This paper introduces the SymbolFit package, which automates the discovery of parametric functions for modeling high-energy physics (HEP) data through symbolic regression. By eliminating the need for manual intuition in function selection, the approach enables a data-driven exploration of function space, resulting in effective fits for complex datasets. The method was validated on CMS and ATLAS Run 2 dijet spectra, achieving a high success rate in rediscovering known functions while maintaining a good fit quality indicated by $\chi^2/\text{NDF} \approx 1$.
Automated symbolic regression can rediscover known HEP functions while achieving high-quality fits, streamlining data analysis in particle physics.
In HEP data analyses, finding an adequate function to model binned data has largely relied on a manual process: guess a functional form by intuition, fit, examine, then repeat until successful. We show that this iterative process can be automated by a machine using symbolic regression, which performs a data-driven search over function space without requiring prior knowledge of what an adequate function should look like. We present the SymbolFit package, which pairs symbolic regression with uncertainty modeling to target HEP analysis use cases, and demonstrate it on the CMS and ATLAS Run 2 dijet spectra: 560 independent seeded runs across seven simple fit configurations generated over 1000 functions fitting the spectra with $\chi^2/\text{NDF}\approx 1$, and 111 of the runs rediscovered the very dijet and UA2 functions used in published dijet searches.
