mjvakili
commented
8 years ago ConstEps module intializes the tolerance to some number. In the next iterations, we change it to 75% quantile (50% quantile in the fitst 2 iterations) of the distances in the previous iterations. In principle, you could keep it constant. But we manually change it to whatever we want for the next iterations
Oh, and [1e13,1e13] is the initial tolerance which is supposed to be arbitrarily large, so we only draw random samples from the prior.
@mjvakili In abc_pemcee.py line 87 you call the ConstEps module from abcpmc. What does this do exactly? Does this keep the threshold eps the same for every iteration or is this a 75th percentile threshold ?
It was originally hardcoded with [1e13, 1e13](commented out on line 86), I'm guessing that this was for testing purposes?