Winding number expansion for the canonical approach to finite density simulations

Abstract

The canonical partition function approach was designed to avoid the overlap problem that affects the lattice simulations of nuclear matter at high density. The method employs the projections of the quark determinant on a fix quark number sector. When the quark number is large, the evaluation of the projected determinant becomes numerically unstable. In this paper a different evaluation method based on expanding the determinant in terms of loops winding around the lattice is studied. We show that this method is stable and significantly faster than our original algorithm. This greatly expands the range of quark numbers that we can simulate effectively.