At present, I am considering the influence of different random number seeds on the experimental results。When I tried different random number seeds, the simulation showed different results。Some of the random number seeds make the experimental results better when estimating parameters。However,Some random number seeds make the simulation results not convergent, and there is a big gap with the real parameters.Do I then have any reason to believe that there is no problem with the program?
Does this also happen if you increase warmup.
What does get_adaptation_info tell you (for different seeds)
1 Like