Joachim van der Herten

Postponed until we manage to find a way to accomplish this in GPflow, some of the changes planned might facilitate this.

Great job, this is great to start from. I think we can do some reshaping to make these features more part of the framework and less specific to the qEI...

@1Reinier , I just noticed your issue in the demo repository. I coded it with python 3.5 and TF 1.0.1 so I'm guessing some renaming issues are to be expected....

hi @yangnw, thanks for your interest and feedback! As you have noticed we are currently in the process of stabilizing the code and making sure its properly tested (and they...

I'd like to comment that this isnt to be merged until GPflow/GPflow#480 is addressed, or we hack some way around it.

The first point is an issue indeed. That is currently wrong. I disagree we should automatically detect no feasible points and switch to PoF only. I'd leave that out of...

Not sure if you were referring to the SciPy optimization of the model likelihood (as described by @nknudde ) or the optimization of the acquisition function which applies a similar...

Hi @mccajm , thank you for your interest in GPFlowOpt. With regards to constraints, there are two distinct use cases: - *black-box* constraints which are part of the expensive evaluation...

Recall that we do not intend to support a wide range of methods, I'd only include others if there is a specific reason for it.

Hi @nrontsis thank you for your interest in GPflowOpt! Batch optimization is definitely on our list. In fact, I have some local code and some preliminary tests on it but...