Least square based method for obtaining one-particle spectral functions from temperature Green functions

A least square based fitting scheme is proposed to extract an optimal one-particle spectral function from any one-particle temperature Green function. It uses the existing non-negative least square (NNLS) fit algorithm to do the fit, and Tikhonov regularization to help with possible numerical singular behaviors. By flexibly adding delta peaks to represent very sharp features of the target spectrum, this scheme guarantees a global minimization of the fitted residue. The performance of this scheme is manifested with diverse physical examples. The proposed scheme is shown to be comparable in performance to the standard Padé analytic continuation scheme.