-
Notifications
You must be signed in to change notification settings - Fork 0
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
Non-isotropic length scales for graph-based Gaussian processes #23
Conversation
1314f14
to
f972c0d
Compare
On hold until fix from stan-dev/math#3084 is released. |
@tillahoffmann has this been updated? for the stan libs? |
Quick update: it looks like the new release date for the bugfix we need is November 11 (see here for details). |
a405cd0
to
7242247
Compare
It looks like the next release date has been pushed back to late November/early Decembers so we'll have to wait a little longer to merge this feature. |
We'll have to weight for the next release candidate because the |
a4d4487
to
8617e43
Compare
8617e43
to
cfac636
Compare
@skiptoniam, thanks for the patience with this PR. I'll release a new Python package shortly and also port the changes over to the R package. I'll post another update here once that's done. |
This has now been published on PyPI as |
This PR allows graph-based Gaussian processes to have different length scales along different dimensions of the covariate space.