Nested study about optuna HOT 5 OPEN

Or maybe what I need is just a function to "return" the objective value so I can just do the loop manually and "return" the value to the two studies.

from optuna.

Oh wow I just realized it exists now with study.ask and study.tell! Guess I'll just try this.

from optuna.

Oh I just realized the different datasets will have different objective value scale and distribution. This won't work unless it's handled, and I don't have any idea how or if it's even possible at all.

Maybe it can be done at sampler level when it separates the good and bad parameters.

from optuna.

The optuna way to do that is to use conditional search space. optuna.samplers.TPESampler with multivariate=True option does handle each group of parameters in multivariate way.

from optuna.

As for optuna-dashboard support, there are issues like optuna/optuna-dashboard#734.

from optuna.