def test_async_ego_keeps_track_of_pending_points() -> None:
search_space = Box(tf.constant([-2.2, -1.0]), tf.constant([1.3, 3.3]))
acq = _GreedyBatchModelMinusMeanMaximumSingleBuilder()
async_rule: AsynchronousGreedy[Box] = AsynchronousGreedy(acq)
dataset = Dataset(tf.zeros([0, 2]), tf.zeros([0, 1]))
state_fn = async_rule.acquire_single(search_space, dataset, QuadraticMeanAndRBFKernel())
state, point1 = state_fn(None)
state, point2 = state_fn(state)
assert state is not None
assert len(state.pending_points) == 2
# let's pretend we saw observations for the first point
new_observations = Dataset(
query_points=point1,
observations=tf.constant([[1]], dtype=tf.float32),
)
state_fn = async_rule.acquire_single(
search_space, dataset + new_observations, QuadraticMeanAndRBFKernel()
)
state, point3 = state_fn(state)
assert state is not None
assert len(state.pending_points) == 2
# two points from the first batch and all points from second
npt.assert_allclose(state.pending_points, tf.concat([point2, point3], axis=0))
def test_async_keeps_track_of_pending_points(
async_rule: AcquisitionRule[State[TensorType, AsynchronousRuleState], Box]
) -> None:
search_space = Box(tf.constant([-2.2, -1.0]), tf.constant([1.3, 3.3]))
dataset = Dataset(tf.zeros([0, 2]), tf.zeros([0, 1]))
state_fn = async_rule.acquire_single(search_space, QuadraticMeanAndRBFKernel(), dataset=dataset)
state, point1 = state_fn(None)
state, point2 = state_fn(state)
assert state is not None
assert len(state.pending_points) == 2
# pretend we saw observation for the first point
new_observations = Dataset(
query_points=point1,
observations=tf.constant([[1]], dtype=tf.float32),
)
state_fn = async_rule.acquire_single(
search_space,
QuadraticMeanAndRBFKernel(),
dataset=dataset + new_observations,
)
state, point3 = state_fn(state)
assert state is not None
assert len(state.pending_points) == 2
# we saw first point, so pendings points are
# second point and new third point
npt.assert_allclose(state.pending_points, tf.concat([point2, point3], axis=0))
def test_sparse_variational_update_updates_num_data() -> None:
model = SparseVariational(
_svgp(tf.zeros([1, 4])),
Dataset(tf.zeros([3, 4]), tf.zeros([3, 1])),
)
model.update(Dataset(tf.zeros([5, 4]), tf.zeros([5, 1])))
assert model.model.num_data == 5
def test_bayesian_optimizer_optimize_tracked_state() -> None:
class _CountingRule(AcquisitionRule[int, Box]):
def acquire(
self,
search_space: Box,
datasets: Mapping[str, Dataset],
models: Mapping[str, ProbabilisticModel],
state: Optional[int],
) -> Tuple[TensorType, int]:
new_state = 0 if state is None else state + 1
return tf.constant([[10.0]]) + new_state, new_state
class _DecreasingVarianceModel(QuadraticMeanAndRBFKernel,
TrainableProbabilisticModel):
def __init__(self, data: Dataset):
super().__init__()
self._data = data
def predict(self,
query_points: TensorType) -> Tuple[TensorType, TensorType]:
mean, var = super().predict(query_points)
return mean, var / len(self._data)
def update(self, dataset: Dataset) -> None:
self._data = dataset
def optimize(self, dataset: Dataset) -> None:
pass
_, history = (BayesianOptimizer(
_quadratic_observer, one_dimensional_range(0, 1)).optimize(
3, {
"": zero_dataset()
}, {
"": _DecreasingVarianceModel(zero_dataset())
}, _CountingRule()).astuple())
assert [record.acquisition_state for record in history] == [None, 0, 1]
assert_datasets_allclose(history[0].datasets[""], zero_dataset())
assert_datasets_allclose(
history[1].datasets[""],
Dataset(tf.constant([[0.0], [10.0]]), tf.constant([[0.0], [100.0]])),
)
assert_datasets_allclose(
history[2].datasets[""],
Dataset(tf.constant([[0.0], [10.0], [11.0]]),
tf.constant([[0.0], [100.0], [121.0]])),
)
for step in range(3):
_, variance_from_saved_model = history[step].models[""].predict(
tf.constant([[0.0]]))
npt.assert_allclose(variance_from_saved_model, 1.0 / (step + 1))
def test_gaussian_process_deep_copyable(
gpr_interface_factory: ModelFactoryType) -> None:
x = tf.constant(np.arange(5).reshape(-1, 1), dtype=gpflow.default_float())
model, _ = gpr_interface_factory(x, fnc_2sin_x_over_3(x))
model_copy = copy.deepcopy(model)
x_predict = tf.constant([[50.5]], gpflow.default_float())
# check deepcopy predicts same values as original
mean_f, variance_f = model.predict(x_predict)
mean_f_copy, variance_f_copy = model_copy.predict(x_predict)
npt.assert_equal(mean_f, mean_f_copy)
npt.assert_equal(variance_f, variance_f_copy)
# check that updating the original doesn't break or change the deepcopy
x_new = tf.concat(
[x, tf.constant([[10.0], [11.0]], dtype=gpflow.default_float())], 0)
new_data = Dataset(x_new, fnc_2sin_x_over_3(x_new))
model.update(new_data)
model.optimize(new_data)
mean_f_updated, variance_f_updated = model.predict(x_predict)
mean_f_copy_updated, variance_f_copy_updated = model_copy.predict(
x_predict)
npt.assert_equal(mean_f_copy_updated, mean_f_copy)
npt.assert_equal(variance_f_copy_updated, variance_f_copy)
npt.assert_array_compare(operator.__ne__, mean_f_updated, mean_f)
npt.assert_array_compare(operator.__ne__, variance_f_updated, variance_f)
class ReducerTestData:
type_class: Type[Union[Sum, Product]]
raw_reduce_op: Callable[[Sequence], float]
dataset: Dataset = Dataset(
np.arange(5, dtype=np.float64).reshape(-1, 1),
np.zeros(5).reshape(-1, 1))
query_point: tf.Tensor = tf.convert_to_tensor(np.array([[0.1], [0.2]]))
def test_expected_constrained_improvement_is_constraint_when_no_feasible_points(
) -> None:
class _Constraint(AcquisitionFunctionBuilder):
def prepare_acquisition_function(
self, datasets: Mapping[str, Dataset],
models: Mapping[str,
ProbabilisticModel]) -> AcquisitionFunction:
def acquisition(x: TensorType) -> TensorType:
x_ = tf.squeeze(x, -2)
return tf.cast(tf.logical_and(0.0 <= x_, x_ < 1.0), x.dtype)
return acquisition
data = {
"foo": Dataset(tf.constant([[-2.0], [1.0]]), tf.constant([[4.0],
[1.0]]))
}
models_ = {"foo": QuadraticMeanAndRBFKernel()}
eci = ExpectedConstrainedImprovement(
"foo", _Constraint()).prepare_acquisition_function(data, models_)
constraint_fn = _Constraint().prepare_acquisition_function(data, models_)
xs = tf.linspace([[-10.0]], [[10.0]], 100)
npt.assert_allclose(eci(xs), constraint_fn(xs))
def test_sparse_variational_update_raises_for_invalid_shapes(new_data: Dataset) -> None:
model = SparseVariational(
_svgp(tf.zeros([1, 4])),
Dataset(tf.zeros([3, 4]), tf.zeros([3, 1])),
)
with pytest.raises(ValueError):
model.update(new_data)
def build_stacked_independent_objectives_model(
data: Dataset) -> ModelStack:
gprs = []
for idx in range(2):
single_obj_data = Dataset(
data.query_points, tf.gather(data.observations, [idx], axis=1))
variance = tf.math.reduce_variance(single_obj_data.observations)
kernel = gpflow.kernels.Matern52(
variance, tf.constant([0.2, 0.2], tf.float64))
gpr = gpflow.models.GPR(single_obj_data.astuple(),
kernel,
noise_variance=1e-5)
gpflow.utilities.set_trainable(gpr.likelihood, False)
gprs.append((GaussianProcessRegression(gpr), 1))
return ModelStack(*gprs)
def test_rff_sampler_raises_for_a_non_gpflow_kernel() -> None:
model = QuadraticMeanAndRBFKernel()
dataset = Dataset(tf.constant([[-2.0]]), tf.constant([[4.1]]))
sampler = RandomFourierFeatureThompsonSampler(dataset, model, 100)
with pytest.raises(AssertionError):
sampler.get_trajectory()
def test_vgp_optimize_natgrads_only_updates_variational_params(compile: bool) -> None:
x_observed = np.linspace(0, 100, 10).reshape((-1, 1))
y_observed = _3x_plus_gaussian_noise(x_observed)
data = x_observed, y_observed
dataset = Dataset(*data)
class DummyBatchOptimizer(BatchOptimizer):
def optimize(self, model: tf.Module, dataset: Dataset) -> None:
pass
optimizer = DummyBatchOptimizer(tf.optimizers.Adam(), compile=compile, max_iter=10)
model = VariationalGaussianProcess(
vgp_matern_model(x_observed[:10], y_observed[:10]), optimizer=optimizer, use_natgrads=True
)
old_num_trainable_params = len(model.trainable_variables)
old_kernel_params = model.get_kernel().parameters[0].numpy()
old_q_mu = model.model.q_mu.numpy()
old_q_sqrt = model.model.q_sqrt.numpy()
model.optimize(dataset)
new_num_trainable_params = len(model.trainable_variables)
new_kernel_params = model.get_kernel().parameters[0].numpy()
new_q_mu = model.model.q_mu.numpy()
new_q_sqrt = model.model.q_sqrt.numpy()
npt.assert_allclose(old_kernel_params, new_kernel_params, atol=1e-3)
npt.assert_equal(old_num_trainable_params, new_num_trainable_params)
npt.assert_raises(AssertionError, npt.assert_allclose, old_q_mu, new_q_mu)
npt.assert_raises(AssertionError, npt.assert_allclose, old_q_sqrt, new_q_sqrt)
def test_model_stack_training() -> None:
class Model(GaussianProcess, TrainableProbabilisticModel):
def __init__(
self,
mean_functions: Sequence[Callable[[TensorType], TensorType]],
kernels: Sequence[tfp.math.psd_kernels.PositiveSemidefiniteKernel],
output_dims: slice,
):
super().__init__(mean_functions, kernels)
self._output_dims = output_dims
def _assert_data(self, dataset: Dataset) -> None:
qp, obs = dataset.astuple()
expected_obs = data.observations[..., self._output_dims]
assert_datasets_allclose(dataset, Dataset(qp, expected_obs))
optimize = _assert_data
update = _assert_data
rbf = tfp.math.psd_kernels.ExponentiatedQuadratic()
model01 = Model([quadratic, quadratic], [rbf, rbf], slice(0, 2))
model2 = Model([quadratic], [rbf], slice(2, 3))
model3 = Model([quadratic], [rbf], slice(3, 4))
stack = ModelStack((model01, 2), (model2, 1), (model3, 1))
data = Dataset(tf.random.uniform([5, 7, 3]), tf.random.uniform([5, 7, 4]))
stack.update(data)
stack.optimize(data)
def test_greedy_batch_acquisition_rule_acquire(
rule_fn: Callable[
# callable input type(s)
[_GreedyBatchModelMinusMeanMaximumSingleBuilder],
# callable output type
AcquisitionRule[TensorType, Box]
| AcquisitionRule[State[TensorType, AsynchronousGreedy.State], Box],
],
num_query_points: int,
) -> None:
search_space = Box(tf.constant([-2.2, -1.0]), tf.constant([1.3, 3.3]))
acq = _GreedyBatchModelMinusMeanMaximumSingleBuilder()
assert acq._update_count == 0
acq_rule: AcquisitionRule[TensorType, Box] | AcquisitionRule[
State[TensorType, AsynchronousGreedy.State], Box
] = rule_fn(acq)
dataset = Dataset(tf.zeros([0, 2]), tf.zeros([0, 1]))
points_or_stateful = acq_rule.acquire_single(search_space, dataset, QuadraticMeanAndRBFKernel())
if callable(points_or_stateful):
_, query_points = points_or_stateful(None)
else:
query_points = points_or_stateful
assert acq._update_count == num_query_points - 1
npt.assert_allclose(query_points, [[0.0, 0.0]] * num_query_points, atol=1e-3)
points_or_stateful = acq_rule.acquire_single(search_space, dataset, QuadraticMeanAndRBFKernel())
if callable(points_or_stateful):
_, query_points = points_or_stateful(None)
else:
query_points = points_or_stateful
npt.assert_allclose(query_points, [[0.0, 0.0]] * num_query_points, atol=1e-3)
assert acq._update_count == 2 * num_query_points - 1
def test_rff_sampler_returns_correctly_shaped_samples(
sample_min_value: bool, sample_size: int
) -> None:
search_space = Box([0.0, 0.0], [1.0, 1.0])
model = QuadraticMeanAndRBFKernel(noise_variance=tf.constant(1.0, dtype=tf.float64))
model.kernel = (
gpflow.kernels.RBF()
) # need a gpflow kernel object for random feature decompositions
x_range = tf.linspace(0.0, 1.0, 5)
x_range = tf.cast(x_range, dtype=tf.float64)
xs = tf.reshape(tf.stack(tf.meshgrid(x_range, x_range, indexing="ij"), axis=-1), (-1, 2))
ys = quadratic(xs)
dataset = Dataset(xs, ys)
sampler = RandomFourierFeatureThompsonSampler(
sample_size, model, dataset, num_features=100, sample_min_value=sample_min_value
)
query_points = search_space.sample(100)
thompson_samples = sampler.sample(query_points)
if sample_min_value:
tf.debugging.assert_shapes([(thompson_samples, [sample_size, 1])])
else:
tf.debugging.assert_shapes([(thompson_samples, [sample_size, 2])])
def test_rff_sampler_raises_for_invalid_sample_size(
sample_size: int,
) -> None:
model = QuadraticMeanAndRBFKernel()
dataset = Dataset(tf.constant([[-2.0]]), tf.constant([[4.1]]))
with pytest.raises(TF_DEBUGGING_ERROR_TYPES):
RandomFourierFeatureThompsonSampler(sample_size, model, dataset)
def test_batch_monte_carlo_expected_improvement_raises_for_empty_data(
) -> None:
builder = BatchMonteCarloExpectedImprovement(100)
data = Dataset(tf.zeros([0, 2]), tf.zeros([0, 1]))
model = QuadraticMeanAndRBFKernel()
with pytest.raises(TF_DEBUGGING_ERROR_TYPES):
builder.prepare_acquisition_function(data, model)
def test_expected_constrained_improvement_min_feasibility_probability_bound_is_inclusive(
) -> None:
pof = tfp.bijectors.Sigmoid().forward
class _Constraint(AcquisitionFunctionBuilder):
def prepare_acquisition_function(
self, datasets: Mapping[str, Dataset],
models: Mapping[str,
ProbabilisticModel]) -> AcquisitionFunction:
return pof
models_ = {"foo": QuadraticMeanAndRBFKernel()}
data = {
"foo": Dataset(tf.constant([[1.1], [2.0]]), tf.constant([[1.21],
[4.0]]))
}
eci = ExpectedConstrainedImprovement(
"foo", _Constraint(),
min_feasibility_probability=pof(1.0)).prepare_acquisition_function(
data, models_)
ei = ExpectedImprovement().using("foo").prepare_acquisition_function(
data, models_)
x = tf.constant([[1.5]])
npt.assert_allclose(eci(x), ei(x) * pof(x))
def test_locally_penalized_acquisitions_match_base_acquisition(
base_builder, ) -> None:
data = Dataset(tf.zeros([3, 2], dtype=tf.float64),
tf.ones([3, 2], dtype=tf.float64))
search_space = Box([0, 0], [1, 1])
model = QuadraticMeanAndRBFKernel()
lp_acq_builder = LocalPenalizationAcquisitionFunction(
search_space, base_acquisition_function_builder=base_builder)
lp_acq = lp_acq_builder.prepare_acquisition_function(data, model, None)
base_acq = base_builder.prepare_acquisition_function(data, model)
x_range = tf.linspace(0.0, 1.0, 11)
x_range = tf.cast(x_range, dtype=tf.float64)
xs = tf.reshape(
tf.stack(tf.meshgrid(x_range, x_range, indexing="ij"), axis=-1),
(-1, 2))
lp_acq_values = lp_acq(xs[..., None, :])
base_acq_values = base_acq(xs[..., None, :])
if isinstance(base_builder, ExpectedImprovement):
npt.assert_array_equal(lp_acq_values, base_acq_values)
else: # check sampling-based acquisition functions are close
npt.assert_allclose(lp_acq_values, base_acq_values, atol=0.001)
def test_ego(search_space: SearchSpace, expected_minimum: tf.Tensor) -> None:
ego = EfficientGlobalOptimization(
NegativeLowerConfidenceBound(0).using(OBJECTIVE))
dataset = Dataset(tf.zeros([0, 2]), tf.zeros([0, 1]))
query_point, _ = ego.acquire(search_space, {OBJECTIVE: dataset},
{OBJECTIVE: QuadraticMeanAndRBFKernel()})
npt.assert_array_almost_equal(query_point, expected_minimum, decimal=5)
def build_stacked_independent_objectives_model(data: Dataset,
num_output) -> ModelStack:
gprs = []
for idx in range(num_output):
single_obj_data = Dataset(data.query_points,
tf.gather(data.observations, [idx], axis=1))
variance = tf.math.reduce_variance(single_obj_data.observations)
kernel = gpflow.kernels.Matern52(variance)
gpr = gpflow.models.GPR(
(single_obj_data.query_points, single_obj_data.observations),
kernel,
noise_variance=1e-5)
gpflow.utilities.set_trainable(gpr.likelihood, False)
gprs.append((create_model(
GPflowModelConfig(
**{
"model": gpr,
"optimizer": gpflow.optimizers.Scipy(),
"optimizer_args": {
"minimize_args": {
"options": dict(maxiter=100)
}
}
})), 1))
return ModelStack(*gprs)
def test_trust_region_for_unsuccessful_local_to_global_trust_region_reduced(
) -> None:
tr = TrustRegion(NegativeLowerConfidenceBound(0).using(OBJECTIVE))
dataset = Dataset(tf.constant([[0.1, 0.2], [-0.1, -0.2]]),
tf.constant([[0.4], [0.5]]))
lower_bound = tf.constant([-2.2, -1.0])
upper_bound = tf.constant([1.3, 3.3])
search_space = Box(lower_bound, upper_bound)
eps = 0.5 * (search_space.upper - search_space.lower) / 10
previous_y_min = dataset.observations[0]
is_global = False
acquisition_space = Box(dataset.query_points[0] - eps,
dataset.query_points[0] + eps)
previous_state = TrustRegion.State(acquisition_space, eps, previous_y_min,
is_global)
_, current_state = tr.acquire(search_space, {OBJECTIVE: dataset},
{OBJECTIVE: QuadraticMeanAndRBFKernel()},
previous_state)
npt.assert_array_less(
current_state.eps,
previous_state.eps) # current TR smaller than previous
assert current_state.is_global
npt.assert_array_almost_equal(current_state.acquisition_space.lower,
lower_bound)
def test_joint_batch_acquisition_rule_acquire(
rule_fn: Callable[
# callable input type(s)
[_JointBatchModelMinusMeanMaximumSingleBuilder, int],
# callable output type
AcquisitionRule[TensorType, Box]
| AcquisitionRule[State[TensorType, AsynchronousRuleState], Box],
]
) -> None:
search_space = Box(tf.constant([-2.2, -1.0]), tf.constant([1.3, 3.3]))
num_query_points = 4
acq = _JointBatchModelMinusMeanMaximumSingleBuilder()
acq_rule: AcquisitionRule[TensorType, Box] | AcquisitionRule[
State[TensorType, AsynchronousRuleState], Box
] = rule_fn(acq, num_query_points)
dataset = Dataset(tf.zeros([0, 2]), tf.zeros([0, 1]))
points_or_stateful = acq_rule.acquire_single(
search_space, QuadraticMeanAndRBFKernel(), dataset=dataset
)
if callable(points_or_stateful):
_, query_point = points_or_stateful(None)
else:
query_point = points_or_stateful
print(query_point)
npt.assert_allclose(query_point, [[0.0, 0.0]] * num_query_points, atol=1e-3)
def test_dataset_raises_for_invalid_ranks(
query_points_shape: ShapeLike, observations_shape: ShapeLike) -> None:
query_points = tf.zeros(query_points_shape)
observations = tf.ones(observations_shape)
with pytest.raises(ValueError):
Dataset(query_points, observations)
def test_trust_region_successful_global_to_global_trust_region_unchanged(
rule: AcquisitionRule[TensorType, Box], expected_query_point: TensorType
) -> None:
tr = TrustRegion(rule)
dataset = Dataset(tf.constant([[0.1, 0.2], [-0.1, -0.2]]), tf.constant([[0.4], [0.3]]))
lower_bound = tf.constant([-2.2, -1.0])
upper_bound = tf.constant([1.3, 3.3])
search_space = Box(lower_bound, upper_bound)
eps = 0.5 * (search_space.upper - search_space.lower) / 10
previous_y_min = dataset.observations[0]
is_global = True
previous_state = TrustRegion.State(search_space, eps, previous_y_min, is_global)
current_state, query_point = tr.acquire(
search_space,
{OBJECTIVE: QuadraticMeanAndRBFKernel()},
datasets={OBJECTIVE: dataset},
)(previous_state)
assert current_state is not None
npt.assert_array_almost_equal(current_state.eps, previous_state.eps)
assert current_state.is_global
npt.assert_array_almost_equal(query_point, expected_query_point, 5)
npt.assert_array_almost_equal(current_state.acquisition_space.lower, lower_bound)
npt.assert_array_almost_equal(current_state.acquisition_space.upper, upper_bound)
def test_rff_sampler_returns_same_posterior_from_each_calculation_method(
) -> None:
model = QuadraticMeanAndRBFKernel(
noise_variance=tf.constant(1.0, dtype=tf.float64))
model.kernel = (
gpflow.kernels.RBF()
) # need a gpflow kernel object for random feature decompositions
x_range = tf.linspace(0.0, 1.0, 5)
x_range = tf.cast(x_range, dtype=tf.float64)
xs = tf.reshape(
tf.stack(tf.meshgrid(x_range, x_range, indexing="ij"), axis=-1),
(-1, 2))
ys = quadratic(xs)
dataset = Dataset(xs, ys)
sampler = RandomFourierFeatureThompsonSampler(dataset, model, 100)
sampler.get_trajectory()
posterior_1 = sampler._prepare_theta_posterior_in_design_space()
posterior_2 = sampler._prepare_theta_posterior_in_gram_space()
npt.assert_allclose(posterior_1.loc, posterior_2.loc, rtol=0.02)
npt.assert_allclose(posterior_1.scale_tril,
posterior_2.scale_tril,
rtol=0.02)
def test_trust_region_for_successful_local_to_global_trust_region_increased(
rule: AcquisitionRule[TensorType, Box]
) -> None:
tr = TrustRegion(rule)
dataset = Dataset(tf.constant([[0.1, 0.2], [-0.1, -0.2]]), tf.constant([[0.4], [0.3]]))
lower_bound = tf.constant([-2.2, -1.0])
upper_bound = tf.constant([1.3, 3.3])
search_space = Box(lower_bound, upper_bound)
eps = 0.5 * (search_space.upper - search_space.lower) / 10
previous_y_min = dataset.observations[0]
is_global = False
acquisition_space = Box(dataset.query_points[0] - eps, dataset.query_points[0] + eps)
previous_state = TrustRegion.State(acquisition_space, eps, previous_y_min, is_global)
current_state, _ = tr.acquire(
search_space,
{OBJECTIVE: QuadraticMeanAndRBFKernel()},
datasets={OBJECTIVE: dataset},
)(previous_state)
assert current_state is not None
npt.assert_array_less(previous_state.eps, current_state.eps) # current TR larger than previous
assert current_state.is_global
npt.assert_array_almost_equal(current_state.acquisition_space.lower, lower_bound)
npt.assert_array_almost_equal(current_state.acquisition_space.upper, upper_bound)
def test_gaussian_process_regression_default_optimize(gpr_interface_factory) -> None:
data = _mock_data()
model = gpr_interface_factory(*data)
internal_model = model.model
loss = internal_model.training_loss()
model.optimize(Dataset(*data))
assert internal_model.training_loss() < loss
def test_trust_region_for_unsuccessful_global_to_local_trust_region_unchanged(
) -> None:
tr = TrustRegion(NegativeLowerConfidenceBound(0).using(OBJECTIVE))
dataset = Dataset(tf.constant([[0.1, 0.2], [-0.1, -0.2]]),
tf.constant([[0.4], [0.5]]))
lower_bound = tf.constant([-2.2, -1.0])
upper_bound = tf.constant([1.3, 3.3])
search_space = Box(lower_bound, upper_bound)
eps = 0.5 * (search_space.upper - search_space.lower) / 10
previous_y_min = dataset.observations[0]
is_global = True
acquisition_space = search_space
previous_state = TrustRegion.State(acquisition_space, eps, previous_y_min,
is_global)
query_point, current_state = tr.acquire(
search_space, {OBJECTIVE: dataset},
{OBJECTIVE: QuadraticWithUnitVariance()}, previous_state)
npt.assert_array_almost_equal(current_state.eps, previous_state.eps)
assert not current_state.is_global
npt.assert_array_less(lower_bound, current_state.acquisition_space.lower)
npt.assert_array_less(current_state.acquisition_space.upper, upper_bound)
assert query_point[0] in current_state.acquisition_space
def test_mc_ind_acquisition_function_builder_approximates_model_samples() -> None:
class _Acq(MCIndAcquisitionFunctionBuilder):
def _build_with_sampler(
self,
datasets: Mapping[str, Dataset],
models: Mapping[str, ProbabilisticModel],
samplers: Mapping[str, IndependentReparametrizationSampler],
) -> AcquisitionFunction:
assert samplers.keys() == {"foo", "bar", "baz"}
x = tf.random.uniform([100, 2], minval=-10.0, maxval=10.0, dtype=tf.float64)
for key in samplers:
samples = samplers[key].sample(x)
mean, var = models[key].predict(x)
_assert_kolmogorov_smirnov_95(
tf.linalg.matrix_transpose(samples),
tfp.distributions.Normal(mean[..., None], tf.sqrt(var)[..., None]),
)
return raise_
data = Dataset(tf.zeros([0, 2], dtype=tf.float64), tf.zeros([0, 2], dtype=tf.float64))
_Acq(20_000).prepare_acquisition_function(
{"foo": data, "bar": data, "baz": data},
{
"foo": _dim_two_gp((0.5, 0.5)),
"bar": _dim_two_gp((1.3, 1.3)),
"baz": _dim_two_gp((-0.7, -0.7)),
},
)
def test_augmented_expected_improvement_builder_raises_for_empty_data(
) -> None:
data = Dataset(tf.zeros([0, 1]), tf.ones([0, 1]))
with pytest.raises(ValueError):
AugmentedExpectedImprovement().prepare_acquisition_function(
data, QuadraticMeanAndRBFKernel())