Bernard Beckerman comments

Results 36 comments of


                                            Bernard Beckerman

Multi-objective experiments generate duplicated data

> * Your website states that the Developer API supports more customization. Since we want to use different optimization methods for benchmarking, that is why we chose this option. >...

applying complex constrains

We've recently deprecated discussions, which unfortunately killed @Balandat's link above. For posterity I'm copying the question and answer this refers to here. Question from [Stefan2016](https://github.com/Stefan2016) [on Aug 25, 2023](https://github.com/facebook/Ax/discussions/1797#discussion-5557991) >...

`_random_seed` not retained when using `ax_client.save_to_json_file()` and `AxClient.load_from_json_file()`

Hi @sgbaird, thanks for the crystal clear issue and repro! Taking a look now.

`_random_seed` not retained when using `ax_client.save_to_json_file()` and `AxClient.load_from_json_file()`

This seems like an oversight on our part, but unfortunately I won't be able to implement the fix before I leave (am going out of town for a few weeks)....

ax.dev, GitHub readme, and loop tutorial examples are ignoring `minimize` kwarg

Thanks for this great writeup with repro as usual @sgbaird! Taking a look now.

ax.dev, GitHub readme, and loop tutorial examples are ignoring `minimize` kwarg

This is a bug! And the fix is up : ) ([link](https://github.com/facebook/Ax/pull/2251)) Thanks for this detailed report - made it super easy to find + fix.

Error: A list of 'ChoiceParameter' is not iterable

Closing this out since it looks like this has been addressed. Thanks for raising this @Runyu-Zhang!

Can't control arguments in fit_gpytorch_mll under the hood. Getting ABNORMAL_TERMINATION_IN_LNSRCH warning

@Jgmedina95 thanks for posting! Let me find someone internally that can answer your question and get back to you. In the mean time can you provide a bit more information...

Can't control arguments in fit_gpytorch_mll under the hood. Getting ABNORMAL_TERMINATION_IN_LNSRCH warning

Closing this out due to lack of response. @Jgmedina95 if you're still having issues here, please feel free to comment on and reopen this issue : )

batch of suggestions

@Fa20 There are rules of thumb for the minimum number of trials to achieve a reasonable model (roughly 2*n_parameters) but no strict guidelines on when you should stop sampling, since...