MLJTuning.jl
MLJTuning.jl copied to clipboard
Higher dimensional ranges and nested ranges specification
One dimensional range in MLJBase, how does that fit with MLJTuning and with the generalisation where you may want to specify “spaces” for sets of parameters.
It might be interesting to see how this is done in other optimisation packages in Julia such as JUMP.
Looking beyond Julia, there MLRMBO which can handle seriously complex parameter spaces see example. MLR3 has a parameter package called paradox - nested conditions can be described as outlined here nested parameter conditions.