Neeratyoy Mallik
Neeratyoy Mallik
Hi The implementation details were verified and cross-checked by the then `official` implementation of [HyperBand as seen here](https://github.com/automl/HpBandSter/blob/master/hpbandster/optimizers/hyperband.py#L92). Therefore, in our experiments, the comparison of DEHB with HB and BOHB...
@eddiebergman what do we do with the interrupted evaluation? assuming it is a deep learning model training as an evaluation, is it okay to still exceed the runtime to trigger...
Can we link this issue to the docs or stylecheck related issues/PRs?
can we do better than this
What exactly is the error and under what conditions?
> Is this intented? Don't think so. Likely an artifact from the general SearchSpace.
I agree. There are 2 ways to tackle this: * Either this is its own push that is handled along with the #28, or * This is taken care of...
Hi @AwePhD Sorry for the late response and thanks for the reproducible example Looking at the example and what you described, the behaviour seen is expected The short answer is...
> IMO for a practical HPO user, the first thing accessible should be the number of rungs and their values, then a place in the documentation to see how they...
> a new specific issue for this Hmm fair point. I would probably create a `Feature request` issue for editing docs and examples and some more utils functions. Will leave...