ntamas / plfit

Fitting power-law distributions to empirical data, according to the method of Clauset, Shalizi and Newman
GNU General Public License v2.0
47 stars 17 forks source link

Use BFGS instead of brute-force search for the optimal alpha in the discrete case #1

Closed ntamas closed 13 years ago

ntamas commented 13 years ago

Should be pretty straightforward as there are plenty of open-source BFGS implementations out there. We only have to work out the derivative of the log-likelihood w.r.t. alpha.