-
Notifications
You must be signed in to change notification settings - Fork 1
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
Implement log_abs_det_jacobian for the SoftmaxTransform? #123
Comments
This is tricky because
Question: Can we support both use cases? |
log_abs_det_jacobian
for the BoltzmannTransform
I'm not sure it is even possible to implement class RelaxedOneHotCategorical(TransformedDistribution):
def __init__(self, ...):
super(RelaxedOneHotCategorical, self).__init__(Gumbel(...), SoftmaxTransform())
def log_prob(self, value):
return ...a custom computation... |
(Maybe a bad idea)
See #113
The text was updated successfully, but these errors were encountered: