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

Add Geometric Optimal Transport #167

Open
CaiYitao opened this issue May 15, 2022 · 4 comments
Open

Add Geometric Optimal Transport #167

CaiYitao opened this issue May 15, 2022 · 4 comments

Comments

@CaiYitao
Copy link

CaiYitao commented May 15, 2022

Is it possible to add Geometric Optimal Transport, which was developed by Lei Na, Gu Xianfeng, and Shingtung Yau (邱成桐), into this library?
It has application in Geometric Deep Learning

@zsteve
Copy link
Member

zsteve commented May 17, 2022

Hi @CaiYitao ,
Thanks for adding this issue! The link to "Geometric Optimal Transport" takes me to a course webpage. Is there a particular algorithm that you have in mind?
Re geometric DL, I think the general idea is to keep this library general, so I think functionality that's specific to training DL models would be more appropriate for a separate package.

@CaiYitao
Copy link
Author

CaiYitao commented May 17, 2022

Thank you for your kind reply!
Yeah, that course has the algorithms for geometric optimal transport. it is based on brenier's potential and monge-ampere equation.

As far as I know, it has a dart datastructure, Geometric Variation Algorithm , Geometric Variation algo 2 and Computation Geometric Algorithm which looks very interesting.
as well as Optimal Partial Transport

@davibarreira
Copy link
Member

@CaiYitao , it seems the link is not working anymore. Do you know where to find the course material?

@CaiYitao
Copy link
Author

Hi @davibarreira You may find them in here https://www3.cs.stonybrook.edu/~gu/

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

3 participants