-
Notifications
You must be signed in to change notification settings - Fork 204
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
SNGP | Laplace RF Precision update inconsistent with the likelihood #258
Comments
hey @nikhil-dce! were you able to get this resolved? ccing @jereliu |
Hi @nikhil-dce ! Yes you are correct the released implementation in UB used Gaussian likelihood - the main reason is to keep code simple, and performance-wise we did not observe a significant difference in ECE (and it seems to hurt OOD a bit). |
Hi @jereliu - Thank you for getting back to me and answering my question. It might be nice to add a comment somewhere in the paper/implementation regarding this deviation from the paper. Thanks again!
|
Thanks Nikhil! Yes will add a note to the implementation in an upcoming code update. Will report here when the pull request merged.
|
For the CIFAR10 example, the precision matrix update (in the LaplaceRandomFeatureCovariance class in Edward) is based on gaussian likelihood, whereas in the loss function cross-entropy is being used.
The batch precision update seems different than in the SNGP paper. The update should be based on equation 9 of the paper. Is this observation correct or am I missing something?
#question
The text was updated successfully, but these errors were encountered: