-
Notifications
You must be signed in to change notification settings - Fork 456
RFF utils for GP function sampling #750
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
Conversation
|
This pull request was exported from Phabricator. Differential Revision: D25806553 |
Summary: Pull Request resolved: meta-pytorch#750 see title Differential Revision: D25806553 fbshipit-source-id: cc84bec0a1ea8e693394857fa37dc76ac495ad6c
3858753 to
eacb794
Compare
|
This pull request was exported from Phabricator. Differential Revision: D25806553 |
|
cc @saitcakmak. Let me know if you have any comments since you've previously worked with RFFs |
saitcakmak
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Ltgm. Much cleaner than my version :)
| weights = torch.randn( | ||
| input_dim, | ||
| num_rff_features, | ||
| dtype=base_kernel.lengthscale.dtype, | ||
| device=base_kernel.lengthscale.device, | ||
| ) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Just a thought: Would there be any benefit to using draw_sobol_normal_samples here?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
interesting thought. probably? night be worth looking into.
Summary: Pull Request resolved: meta-pytorch#750 see title Reviewed By: Balandat Differential Revision: D25806553 fbshipit-source-id: d6b276f8dae7f6e05ddafed11a33754d6ddb5547
|
This pull request was exported from Phabricator. Differential Revision: D25806553 |
eacb794 to
3cba19b
Compare
|
This pull request has been merged in 7c73b6c. |
Summary: see title
Differential Revision: D25806553