Skip to content
Draft
Show file tree
Hide file tree
Changes from all commits
Commits
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
2 changes: 2 additions & 0 deletions RELEASES.md
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,8 @@

#### Closed issues

- Fix TensorFlow custom gradients ignoring the upstream gradient, so scaling an OT loss now scales its supplied gradients consistently.

- Fix ordinary JAX gradients for dense `ot.emd2` and preserve the magnitude and higher-order dependence of gradients supplied to `JaxBackend.set_gradients`, including the envelope gradients in `ot.solve` (Issue #625)
- Fix `ot.semidiscrete_wasserstein2_unif_circle` pairing sorted sample locations with unsorted weights, which broke permutation and rotation invariance for nonuniform weights (Issue #921)
- Fix an out-of-bounds read in `ot.bsp.merge_bijections`: the number of plans was taken from `perms.shape[1]` (the number of samples) instead of `perms.shape[0]`, so merging fewer plans than samples read past the array and merging more silently dropped plans. A `perms` outside the documented `(n_plans, n_samples)` layout, an empty plan stack and rows that are not permutations are now rejected (PR #911, Issue #910)
Expand Down
2 changes: 1 addition & 1 deletion ot/backend.py
Original file line number Diff line number Diff line change
Expand Up @@ -3239,7 +3239,7 @@ def set_gradients(self, val, inputs, grads):
@tf.custom_gradient
def tmp(input):
def grad(upstream):
return grads
return tf.nest.map_structure(lambda g: upstream * g, grads)

return val, grad

Expand Down
37 changes: 37 additions & 0 deletions test/test_backend.py
Original file line number Diff line number Diff line change
Expand Up @@ -1010,6 +1010,43 @@ def test_no_cuda_context_for_cpu_only_work():
)


@pytest.mark.skipif(not tf, reason="TensorFlow not installed")
@pytest.mark.parametrize("coefficient", [0.0, 1.0, -2.0, 7.0])
@pytest.mark.parametrize("compiled", [False, True])
def test_tensorflow_set_gradients_chain_rule(coefficient, compiled):
nx = ot.backend.TensorflowBackend()
x = tf.constant([1.0, 2.0], dtype=tf.float64)
y = tf.constant(3.0, dtype=tf.float64)

def differentiate(x, y):
with tf.GradientTape() as tape:
tape.watch((x, y))
value = nx.set_gradients(
tf.constant(5.0, dtype=x.dtype), (x, y), (2 * x, 3 * y)
)
loss = coefficient * value
return value, tape.gradient(loss, (x, y))

if compiled:
differentiate = tf.function(differentiate)
value, gradients = differentiate(x, y)
np.testing.assert_allclose(value, 5.0)
np.testing.assert_allclose(gradients[0], coefficient * 2 * x)
np.testing.assert_allclose(gradients[1], coefficient * 3 * y)


@pytest.mark.skipif(not tf, reason="TensorFlow not installed")
@pytest.mark.parametrize("coefficient", [0.0, -2.0, 7.0])
def test_tensorflow_emd2_scaled_gradient(coefficient):
a = tf.constant([0.5, 0.5], dtype=tf.float64)
cost = tf.constant([[0.0, 2.0], [3.0, 0.0]], dtype=tf.float64)
with tf.GradientTape() as tape:
tape.watch(cost)
loss = coefficient * ot.emd2(a, a, cost)
gradient = tape.gradient(loss, cost)
np.testing.assert_allclose(gradient, coefficient * np.diag([0.5, 0.5]))


@pytest.mark.parametrize("power,expected,second", [(0, 3., 0.), (1, 6., 3.), (2, 12., 12.)])
def test_jax_supplied_gradients(power, expected, second):
jax = pytest.importorskip("jax")
Expand Down
Loading