-
Notifications
You must be signed in to change notification settings - Fork 64
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
loss return question #8
Comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hello, than you for this awesome project, which is very useful to help me understand the method in NNPU paper. But I am confused
abount the NNPU loss, In the file
pu_loss.py
line 51, the loss output returns gamma * negative_risk. I also saw this in NNPU paperAlgorithm 1 Line 9
. In the paper, author said, the loss go along with negative_risk with a step size discounted by gamma to make mini-batch less overfitted whennegative_risk < -beta
. I can not understand this. Besides, I am confused why there is no positive_risk whennegative_risk < -beta
.Hoping for your reply, thank you.
The text was updated successfully, but these errors were encountered: