Skip to content

Fix concretization error with normalize_function #101

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

Closed
teddykoker wants to merge 1 commit into from
Closed

Fix concretization error with normalize_function #101

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
12 changes: 4 additions & 8 deletions e3nn_jax/_src/activation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,16 +58,12 @@ def normalize_function(phi: Callable[[float], float]) -> Callable[[float], float
# x = jax.random.normal(k, (1_000_000,))
x = normalspace(1_000_001)
c = jnp.mean(phi(x) ** 2) ** 0.5
c = c.item()
scale = jnp.where(jnp.allclose(c, 1.0), 1.0, 1.0 / c)

@ameya98 ameya98 Mar 17, 2026

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

should we also be handling the case where c is close to 0?

@teddykoker teddykoker Mar 17, 2026

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this would only be the case if the activation function was lambda x: 0 or close... figured it wasn't an issue since it wasn't in the original code either


if jnp.allclose(c, 1.0):
return phi
else:

def rho(x):
return phi(x) / c
def rho(x):
return phi(x) * scale

return rho
return rho


def parity_function(phi: Callable[[float], float]) -> int:
Expand Down
Loading