Max Balandat
Max Balandat
> This blocks on the input transform refactor - Until that is done, we tend to have the transformed X where we call the posterior_transform. I don't have much context...
@sdaulton any idea what could be going on here? Given the error and looking through the code it may well be that there are some numerical issues going on (in...
We do something manually like this here: https://github.com/mshvartsman/Ax/blob/submitit-runner/ax/metrics/tensorboard.py#L112-L123 it's a bit pedestrian but it works. Presumably `tf.make_ndarray` doesn't do things much smarter? Depending on how it's implemented it may be...
Thanks for flagging this, your explanation makes sense to me. Were you able to verify that this worked properly before the change in https://github.com/pytorch/botorch/pull/2527?
cc @saitcakmak - I wonder if we need to distinguish the "one-shot learnable" input transforms and those that require joint optimization with the model parameters for settings like this. At...
Thanks for putting this up, excited to see some other optimizers that could be useful in cases where SLSQP just ends up being too slow. > A solution could be...
> So you prefer to include the dependency directly and not rewrite gen_candidates_scipy in a way that one can pass a callable to it which has the same signature as...
@jduerholt any insights from the benchmarking?
cc @SebastianAment re qLogEI having a "hole". The model actually seems fine here (thanks @esantorella for the great diagnostics), so this is probably just b/c the incumbent is so high...