Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Register & add a LICENSE file #1

Open
GiggleLiu opened this issue Nov 7, 2021 · 3 comments
Open

Register & add a LICENSE file #1

GiggleLiu opened this issue Nov 7, 2021 · 3 comments

Comments

@GiggleLiu
Copy link

GiggleLiu commented Nov 7, 2021

Hi, @jbrea This is a very neat package for MADS and it still works in Julia1.7, thanks for writing it. Do you have a plan to register it? I need to use some of its functionality in my own project, but feeling bad if I just copy paste the code.

Also, it would be nice to add a LICENSE file in this project so that people know how to use this package properly.

@jbrea
Copy link
Owner

jbrea commented Nov 7, 2021

Thanks for the kudos :)

I didn't have plans for this package (NOMAD is much more feature rich and other black-box-optimizers worked better for my use cases), but I started registration now. It should be registered in a few days.

@GiggleLiu
Copy link
Author

GiggleLiu commented Nov 7, 2021

Thank you! I just started using the MADS method, so I am wondering what is the major limitation of this implementation?

If the issue is not fundamental, I wish to stick to the Julia native version because there is a need to access intermediate information during training and the native Julia version is much easier to adapt to an iterator style.

@jbrea
Copy link
Owner

jbrea commented Nov 8, 2021

NOMAD has certainly more features (see e.g. TODO in MeshAdaptiveDirectSearch.jl; they also have some variants that rely on fitted surrogates) and is much better tested. For the implementation here I just followed the respective papers; I don't know if there are some more tricks in packages like NOMAD.

I am happy if this package is useful for you!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants