C. Benjamins
C. Benjamins
You can do something like this: ```python ... configurations = [your_default_configuration] smac = HyperparameterOptimizationFacade( scenario, task.evaluate, overwrite=True, # Modify the initial design to use our custom initial design initial_design=HyperparameterOptimizationFacade.get_initial_design( scenario,...
they are sufficiently sorted right now
- The initial design is safe to 100% parallelize. - For the parallel sequential search we need to balance asking for configs and retraining the model to propose better configs....
Thank you for the explanation, makes sense! Feel free to close the issue. Running `np.array(pd.Series({"a":1, "b":2}))` yields `array([1, 2])`.
Two aspects here: 1. If the function is non-deterministic, it should be modeled as such. Therefore the GP should receive a `deterministic` parameter and the kernel composition should be adapted....
closed by #1247
Hi Guinan, by instances, do you mean the evaluation of the target function or are you doing algorithm configuration? Can you release the memory at the end of your target...
@munish7771 This is still an interesting feature for multi-objective, however currently not high on our priority list. Do you work in that area? We are always happy about pull requests.
Hi Bogdan, thanks for your suggestion. We are looking into supporting newer python versions. I sometimes run SMAC in python 3.12 without any problems. We are also in the process...