Open fzyzcjy opened 1 year ago
It has been more than a year, and it seems that other issues mostly are closed and have discussions, thus I guess this issue may be simply forgotten. Thus a small ping - @varungodbole @georgedahl
Yes, Hyperband can be a useful technique. And ASHA potentially as well.
If you want to send a PR, that would be welcome. Try to make it a relatively small change in terms of diff if you can. Perhaps a sentence or phrase could be added when we talk about using quasi-random search to say that we can use techniques of this type to quickly discard points that aren't promising from the search.
Note we currently only briefly link to the hyperband paper in a footnote.
Thank you! I will do that later.
Hi thanks for the playbook! I see some articles showing how Hyperband or ASHA can be used to boost the speed of hyperparameter searching. Shortly speaking, it is:
Thus, I wonder whether it is a good idea to utilize this scheduler (in addition to quasi-random search or bayesian)? IMHO they are somehow orthogonal, and we can use both ASHA and quasi-random search. Then, quasi-random search will propose (quasi) random hyper-parameters while ASHA will throw away some of the bad ones.
I am willing to contribute (e.g. making a PR)!