Skip to content
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

Fix compute_gradient to include frozen parameters #156

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Fix compute_gradient to include frozen parameters #156

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f5427bf
Add test case for shape error when no user gradient
mcfarljm Nov 23, 2022
f28f50e
Fix compute_gradient to include frozen parameters
mcfarljm Nov 23, 2022
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
6 changes: 3 additions & 3 deletions src/george/modeling.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -115,15 +115,15 @@ def compute_gradient(self, *args, **kwargs):

"""
_EPS = 1.254e-5
vector = self.get_parameter_vector()
vector = self.get_parameter_vector(include_frozen=True)
value0 = self.get_value(*args, **kwargs)
grad = np.empty([len(vector)] + list(value0.shape), dtype=np.float64)
for i, v in enumerate(vector):
vector[i] = v + _EPS
self.set_parameter_vector(vector)
self.set_parameter_vector(vector, include_frozen=True)
value = self.get_value(*args, **kwargs)
vector[i] = v
self.set_parameter_vector(vector)
self.set_parameter_vector(vector, include_frozen=True)
grad[i] = (value - value0) / _EPS
return grad

Expand Down
21 changes: 21 additions & 0 deletions tests/test_modeling.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,6 +72,13 @@ def compute_gradient(self, x):
return dict(m=x, b=np.ones(len(x)))


class LinearWhiteNoiseWithoutGrad(Model):
parameter_names = ("m", "b")

def get_value(self, x):
return self.m * x + self.b


def test_gp_callable_white_noise(N=50, seed=1234):
np.random.seed(seed)
x = np.random.uniform(0, 5)
Expand All @@ -86,6 +93,20 @@ def test_gp_callable_white_noise(N=50, seed=1234):
check_gradient(gp, y)


def test_gp_callable_white_noise_without_grad(N=50, seed=1234):
np.random.seed(seed)
x = np.random.uniform(0, 5)
y = 5 + np.sin(x)
gp = GP(10. * kernels.ExpSquaredKernel(1.3), mean=5.0,
white_noise=LinearWhiteNoiseWithoutGrad(-6, 0.01),
fit_white_noise=True)
gp.compute(x)
check_gradient(gp, y)

gp.freeze_parameter("white_noise:m")
check_gradient(gp, y)


def test_parameters():
kernel = 10 * kernels.ExpSquaredKernel(1.0)
kernel += 0.5 * kernels.RationalQuadraticKernel(log_alpha=0.1, metric=5.0)
Expand Down