Speaker
Description
Domain-wall fermions provide a lattice formulation that preserves chiral symmetry to a high degree by introducing an additional fifth dimension. In practical simulations, however, the extent of this direction must remain finite, which leads to residual chiral symmetry breaking characterized by the residual mass. Increasing the fifth-dimensional size can reduce this effect, but it also significantly raises the computational cost. To address this trade-off, we develop a machine-learning-based framework that optimizes the domain-wall fermion parameters so as to minimize the residual mass while keeping the fifth dimension short. Our approach aims to reproduce the improved chiral properties normally obtained with a larger fifth-dimensional extent, thereby enabling more efficient lattice simulations without a substantial increase in computational resources.