Skip to content

Odd number for d_state #160

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

Open
Yaoyx opened this issue Apr 17, 2025 · 0 comments
Open

Odd number for d_state #160

Yaoyx opened this issue Apr 17, 2025 · 0 comments

Comments

@Yaoyx
Copy link

Yaoyx commented Apr 17, 2025

Hi,

Thank you for this fascinating work.
I am still learning the whole concept. One question I have about DPLR and NPLR is that only half of conjugate pairs will be kept, then if we set d_state to an odd number, we will lose one state while reconstructing the matrix, as the code only multiplies the size by a factor of 2.

https://github.com/state-spaces/s4/blob/e757cef57d89e448c413de7325ed5601aceaac13/models/s4/s4.py#L1520C1-L1522C45

So I guess we should always assume d_state to be an even number?

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

1 participant