Skip to content

Update losses.py #253

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.

Sign up for GitHub

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

Merged
cnellington merged 1 commit into from
Sep 23, 2024
Merged

Update losses.py #253

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions contextualized/dags/losses.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,12 +18,12 @@ def dag_loss_dagma(W, s=1, alpha=0.0, **kwargs):

def dag_loss_poly_indiv(w):
d = w.shape[-1]
return torch.trace(torch.eye(d) + (1 / d) * torch.matmul(w, w)) - d
return torch.trace((torch.eye(d) + (1 / d) * torch.matmul(w, w))^d) - d


def dag_loss_poly(W, **kwargs):
"""DAG loss on batched networks W using the
h_poly form: h_poly(W) = Tr((I + 1/d(W*W)^d) - d
h_poly form: h_poly(W) = Tr((I + 1/d(W*W))^d) - d
"""
return torch.mean(torch.Tensor([dag_loss_poly_indiv(w) for w in W]))

Expand Down