def test_negative_lower_confidence_bound_builder_builds_negative_lower_confidence_bound() -> None:
model = QuadraticMeanAndRBFKernel()
beta = 1.96
acq_fn = NegativeLowerConfidenceBound(beta).prepare_acquisition_function(
Dataset(tf.zeros([0, 1]), tf.zeros([0, 1])), model
)
query_at = tf.linspace([-10], [10], 100)
expected = -lower_confidence_bound(model, beta, query_at)
npt.assert_array_almost_equal(acq_fn(query_at), expected)
def test_negative_lower_confidence_bound_builder_builds_negative_lower_confidence_bound(
) -> None:
model = QuadraticWithUnitVariance()
beta = 1.96
acq_fn = NegativeLowerConfidenceBound(beta).prepare_acquisition_function(
Dataset(tf.constant([[]]), tf.constant([[]])), model)
query_at = tf.constant([[-3.], [-2.], [-1.], [0.], [1.], [2.], [3.]])
expected = -lower_confidence_bound(model, beta, query_at)
npt.assert_array_almost_equal(acq_fn(query_at), expected)
def test_reducers_on_lcb(reducer):
m = 6
beta = tf.convert_to_tensor(1.96, dtype=tf.float64)
model = QuadraticWithUnitVariance()
acqs = [NegativeLowerConfidenceBound(beta).using("foo") for _ in range(m)]
acq = reducer.type_class(*acqs)
acq_fn = acq.prepare_acquisition_function({"foo": reducer.dataset}, {"foo": model})
individual_lcb = [-lower_confidence_bound(model, beta, reducer.query_point) for _ in range(m)]
expected = reducer.raw_reduce_op(individual_lcb)
desired = acq_fn(reducer.query_point)
np.testing.assert_array_almost_equal(expected, desired)
def test_lower_confidence_bound(beta: float) -> None:
query_at = tf.constant([[-3.0], [-2.0], [-1.0], [0.0], [1.0], [2.0], [3.0]])
actual = lower_confidence_bound(QuadraticMeanAndRBFKernel(), beta, query_at)
npt.assert_array_almost_equal(actual, query_at ** 2 - beta)
def test_lower_confidence_bound_raises_for_negative_beta(beta: float) -> None:
with pytest.raises(ValueError):
lower_confidence_bound(QuadraticMeanAndRBFKernel(), beta, tf.constant([[]]))
def test_lower_confidence_bound_raises_for_negative_beta(beta: float) -> None:
with pytest.raises(ValueError):
lower_confidence_bound(QuadraticWithUnitVariance(), beta, tf.constant([[]]))
def test_lower_confidence_bound(beta: float) -> None:
query_at = tf.constant([[-3.], [-2.], [-1.], [0.], [1.], [2.], [3.]])
actual = lower_confidence_bound(QuadraticWithUnitVariance(), beta,
query_at)
npt.assert_array_almost_equal(actual, query_at**2 - beta)
def test_lower_confidence_bound_raises_for_negative_beta(beta: float) -> None:
with pytest.raises(ValueError):
lower_confidence_bound(MagicMock(ModelInterface), beta,
tf.constant([[]]))
def test_lower_confidence_bound(beta: float) -> None:
query_at = tf.linspace([[-3]], [[3]], 10)
actual = lower_confidence_bound(QuadraticMeanAndRBFKernel(), beta)(query_at)
npt.assert_array_almost_equal(actual, tf.squeeze(query_at, -2) ** 2 - beta)
def test_lower_confidence_bound_raises_for_invalid_batch_size(at: TensorType) -> None:
lcb = lower_confidence_bound(QuadraticMeanAndRBFKernel(), tf.constant(1.0))
with pytest.raises(TF_DEBUGGING_ERROR_TYPES):
lcb(at)
