-
Notifications
You must be signed in to change notification settings - Fork 51
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
Rff sampler #195
Rff sampler #195
Conversation
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.
Good PR. Documentation and testing is excellent. Few minor comments to address and then we can merge.
seed: KeyArray, | ||
num_features: Optional[int] = 100, | ||
) -> FunctionalSample: | ||
"""Build an approximate sample from the Gaussian process prior. This method |
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.
Think you'll need a raw string or double backslashes.
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.
where?
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.
"""Build
should be r"""Build
seed: KeyArray, | ||
num_features: Optional[int] = 100, | ||
) -> FunctionalSample: | ||
"""Build an approximate sample from the Gaussian process prior. This method |
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.
"""Build
should be r"""Build
params: Dict, | ||
train_data: Dataset, | ||
key: KeyArray, | ||
num_features: Optional[int] = 100, |
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.
Is 100 sensible 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.
yeah actually, you dont need very many for the decoupled sampling!
I have added a method to the GP prior so that we can get approximate samples from the GP. I use the standard RFF approach to get samples with functional forms that can be cheaply queried as many times as we like.