-
Notifications
You must be signed in to change notification settings - Fork 18
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
Fix for issue #95 #96
Conversation
Fun. Seems like fixing the covariance issue introduced another issue o.O |
Seems it was just because of very poorly specified sampler params |
Failures are only on nightly, let's merge! |
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.
Thanks, @torfjelde -- it looks correct to me.
On a side note, the current code should still be correct, albeit suboptimal, since it uses flipped gradient directions?
Nah, because it used flipped gradients only for the log-prob computation, not also for the actual proposal. |
No description provided.