Speaker
Description
In this talk we introduce a machine learning approach to tune an effective relativistic heavy quark action for applications in lattice QCD.
The effective action is the so-called "RHQ" action, which has three open parameters that require non-perturbative tuning to match physics observables associated with Lorentz symmetry, spin-averaged masses, and hyperfine splittings in charmonium and bottomonium systems. We reformulate the tuning procedure as a supervised-learning problem to construct a non-linear map between the action parameters and the tuning observables.
We demonstrate the procedure on two ensembles generated within the OpenLat Initiative. The learned map accurately reproduces the tuning observables in the parameter region of interest. The approach streamlines RHQ tuning on new ensembles and supports future calculations in heavy-hadron spectroscopy.