def test_batch_reparametrization_sampler_sample_raises_for_inconsistent_batch_size(
) -> None:
sampler = BatchReparametrizationSampler(100, QuadraticMeanAndRBFKernel())
sampler.sample(tf.constant([[0.0], [1.0], [2.0]]))
with pytest.raises(TF_DEBUGGING_ERROR_TYPES):
sampler.sample(tf.constant([[0.0], [1.0]]))
def test_batch_reparametrization_sampler_samples_are_distinct_for_new_instances(
) -> None:
model = _dim_two_gp()
sampler1 = BatchReparametrizationSampler(100, model)
sampler2 = BatchReparametrizationSampler(100, model)
xs = tf.random.uniform([3, 5, 7, 2], dtype=tf.float64)
npt.assert_array_less(1e-9,
tf.abs(sampler2.sample(xs) - sampler1.sample(xs)))
def test_batch_reparametrization_sampler_sample_raises_for_negative_jitter() -> None:
sampler = BatchReparametrizationSampler(100, QuadraticMeanAndRBFKernel())
with pytest.raises(TF_DEBUGGING_ERROR_TYPES):
sampler.sample(tf.constant([[0.0]]), jitter=-1e-6)
def test_batch_reparametrization_sampler_sample_raises_for_invalid_at_shape(at: tf.Tensor) -> None:
sampler = BatchReparametrizationSampler(100, QuadraticMeanAndRBFKernel())
with pytest.raises(TF_DEBUGGING_ERROR_TYPES):
sampler.sample(at)
def test_batch_reparametrization_sampler_samples_are_repeatable() -> None:
sampler = BatchReparametrizationSampler(100, _dim_two_gp())
xs = tf.random.uniform([3, 5, 7, 2], dtype=tf.float64)
npt.assert_allclose(sampler.sample(xs), sampler.sample(xs))
def test_batch_reparametrization_sampler_samples_are_continuous() -> None:
sampler = BatchReparametrizationSampler(100, _dim_two_gp())
xs = tf.random.uniform([3, 5, 7, 2], dtype=tf.float64)
npt.assert_array_less(tf.abs(sampler.sample(xs + 1e-20) - sampler.sample(xs)), 1e-20)