Thanks for this very nice repo ! But something isn't very clear to me. As it is said in the blogpost, Hyperband runs configs for just an iteration or two at first, to get a taste of how they perform. Then it takes the best performers and runs them longer.
So I thought that in the outer loop, we would first randomly instantiate the configuration T and then update it at the end of each inner loop.
However this is not the case, and for each new s, a random T is then again drawn, without taking into account the previous computed T. Am I missing something here ?
My bad, I think I know understand different run are meant to be independent. This part of the blogpost was only referring to the succesiveHalving part of the process !
Hello,
Thanks for this very nice repo ! But something isn't very clear to me. As it is said in the blogpost,
Hyperband runs configs for just an iteration or two at first, to get a taste of how they perform. Then it takes the best performers and runs them longer.
So I thought that in the outer loop, we would first randomly instantiate the configuration
T
and then update it at the end of each inner loop.However this is not the case, and for each new
s
, a randomT
is then again drawn, without taking into account the previous computedT
. Am I missing something here ?