def testNoWeightedExamples(self):
# Setup test data with 1 positive, and 1 negative example.
example_protos = [
make_example_proto({
'age': [0],
'gender': [0]
}, 0),
make_example_proto({
'age': [1],
'gender': [1]
}, 1),
]
# Zeroed out example weights.
example_weights = [0.0, 0.0]
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(symmetric_l2_regularization=1,
symmetric_l1_regularization=0,
loss_type='logistic_loss')
lr = SdcaModel(CONTAINER, examples, variables, options)
tf.initialize_all_variables().run()
self.assertAllClose([0.5, 0.5], lr.predictions(examples).eval())
lr.minimize().run()
self.assertAllClose([0.5, 0.5], lr.predictions(examples).eval())
with self.assertRaisesOpError(
'No examples found or all examples have zero weight.'):
lr.approximate_duality_gap().eval()
def testNoWeightedExamples(self):
# Setup test data with 1 positive, and 1 negative example.
example_protos = [
make_example_proto(
{'age': [0],
'gender': [0]}, 0),
make_example_proto(
{'age': [1],
'gender': [1]}, 1),
]
# Zeroed out example weights.
example_weights = [0.0, 0.0]
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(symmetric_l2_regularization=1,
symmetric_l1_regularization=0,
loss_type='logistic_loss')
lr = SdcaModel(CONTAINER, examples, variables, options)
tf.initialize_all_variables().run()
self.assertAllClose([0.5, 0.5], lr.predictions(examples).eval())
lr.minimize().run()
self.assertAllClose([0.5, 0.5], lr.predictions(examples).eval())
with self.assertRaisesOpError(
'No examples found or all examples have zero weight.'):
lr.approximate_duality_gap().eval()
def testSimple(self):
# Setup test data
example_protos = [
make_example_proto(
{'age': [0],
'gender': [0]}, -10.0),
make_example_proto(
{'age': [1],
'gender': [1]}, 14.0),
]
example_weights = [1.0, 1.0]
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(symmetric_l2_regularization=1,
symmetric_l1_regularization=0,
loss_type='squared_loss')
lr = SdcaModel(CONTAINER, examples, variables, options)
tf.initialize_all_variables().run()
predictions = lr.predictions(examples)
for _ in xrange(20):
lr.minimize().run()
# Predictions should be 2/3 of label due to minimizing regularized loss:
# (label - 2 * weight)^2 / 2 + L2 * 2 * weight^2
self.assertAllClose([-20.0 / 3.0, 28.0 / 3.0],
predictions.eval(),
rtol=0.005)
self.assertAllClose(0.01,
lr.approximate_duality_gap().eval(),
rtol=1e-2,
atol=1e-2)
def testSimple(self):
# Setup test data
example_protos = [
make_example_proto({"age": [0], "gender": [0]}, -10.0),
make_example_proto({"age": [1], "gender": [1]}, 14.0),
]
example_weights = [1.0, 1.0]
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(symmetric_l2_regularization=1, symmetric_l1_regularization=0, loss_type="squared_loss")
lr = SdcaModel(examples, variables, options)
tf.initialize_all_variables().run()
predictions = lr.predictions(examples)
train_op = lr.minimize()
for _ in range(_MAX_ITERATIONS):
train_op.run()
# Predictions should be 2/3 of label due to minimizing regularized loss:
# (label - 2 * weight)^2 / 2 + L2 * 2 * weight^2
self.assertAllClose([-20.0 / 3.0, 28.0 / 3.0], predictions.eval(), rtol=0.005)
# Approximate gap should be very close to 0.0. (In fact, because the gap
# is only approximate, it is likely that upon convergence the duality gap
# can have a tiny negative value).
self.assertAllClose(0.0, lr.approximate_duality_gap().eval(), atol=1e-2)
def testSomeUnweightedExamples(self):
# Setup test data with 4 examples, but should produce the same
# results as testSimple.
example_protos = [
# Will be used.
make_example_proto({"age": [0], "gender": [0]}, 0),
# Will be ignored.
make_example_proto({"age": [1], "gender": [0]}, 0),
# Will be used.
make_example_proto({"age": [1], "gender": [1]}, 1),
# Will be ignored.
make_example_proto({"age": [1], "gender": [0]}, 1),
]
example_weights = [1.0, 0.0, 1.0, 0.0]
with self._single_threaded_test_session():
# Only use examples 0 and 2
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(symmetric_l2_regularization=1, symmetric_l1_regularization=0, loss_type="logistic_loss")
lr = SdcaModel(CONTAINER, examples, variables, options)
tf.initialize_all_variables().run()
unregularized_loss = lr.unregularized_loss(examples)
loss = lr.regularized_loss(examples)
predictions = lr.predictions(examples)
train_op = lr.minimize()
for _ in xrange(_MAX_ITERATIONS):
train_op.run()
self.assertAllClose(0.411608, unregularized_loss.eval(), atol=0.05)
self.assertAllClose(0.525457, loss.eval(), atol=0.01)
predicted_labels = get_binary_predictions_for_logistic(predictions)
self.assertAllClose([0, 1, 1, 1], predicted_labels.eval())
self.assertAllClose(0.01, lr.approximate_duality_gap().eval(), rtol=1e-2, atol=1e-2)
def testImbalanced(self):
# Setup test data with 1 positive, and 3 negative examples.
example_protos = [
make_example_proto({"age": [0], "gender": [0]}, 0),
make_example_proto({"age": [2], "gender": [0]}, 0),
make_example_proto({"age": [3], "gender": [0]}, 0),
make_example_proto({"age": [1], "gender": [1]}, 1),
]
example_weights = [1.0, 1.0, 1.0, 1.0]
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(3, 1)
options = dict(symmetric_l2_regularization=1, symmetric_l1_regularization=0, loss_type="logistic_loss")
lr = SdcaModel(CONTAINER, examples, variables, options)
tf.initialize_all_variables().run()
unregularized_loss = lr.unregularized_loss(examples)
loss = lr.regularized_loss(examples)
predictions = lr.predictions(examples)
train_op = lr.minimize()
for _ in xrange(_MAX_ITERATIONS):
train_op.run()
self.assertAllClose(0.226487 + 0.102902, unregularized_loss.eval(), atol=0.08)
self.assertAllClose(0.328394 + 0.131364, loss.eval(), atol=0.01)
predicted_labels = get_binary_predictions_for_logistic(predictions)
self.assertAllEqual([0, 0, 0, 1], predicted_labels.eval())
self.assertAllClose(0.01, lr.approximate_duality_gap().eval(), rtol=1e-2, atol=1e-2)
def testSimpleNoL2(self):
# Same as test above (so comments from above apply) but without an L2.
# The algorithm should behave as if we have an L2 of 1 in optimization but
# 0 in regularized_loss.
example_protos = [
make_example_proto({"age": [0], "gender": [0]}, 0),
make_example_proto({"age": [1], "gender": [1]}, 1),
]
example_weights = [1.0, 1.0]
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(symmetric_l2_regularization=0, symmetric_l1_regularization=0, loss_type="logistic_loss")
lr = SdcaModel(CONTAINER, examples, variables, options)
tf.initialize_all_variables().run()
unregularized_loss = lr.unregularized_loss(examples)
loss = lr.regularized_loss(examples)
predictions = lr.predictions(examples)
self.assertAllClose(0.693147, unregularized_loss.eval())
self.assertAllClose(0.693147, loss.eval())
train_op = lr.minimize()
for _ in xrange(_MAX_ITERATIONS):
train_op.run()
# There is neither L1 nor L2 loss, so regularized and unregularized losses
# should be exactly the same.
self.assertAllClose(0.40244, unregularized_loss.eval(), atol=0.01)
self.assertAllClose(0.40244, loss.eval(), atol=0.01)
predicted_labels = get_binary_predictions_for_logistic(predictions)
self.assertAllEqual([0, 1], predicted_labels.eval())
self.assertAllClose(0.01, lr.approximate_duality_gap().eval(), rtol=1e-2, atol=1e-2)
def testImbalancedWithExampleWeights(self):
# Setup test data with 1 positive, and 1 negative example.
example_protos = [
make_example_proto({
'age': [0],
'gender': [0]
}, 0),
make_example_proto({
'age': [1],
'gender': [1]
}, 1),
]
example_weights = [3.0, 1.0]
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(symmetric_l2_regularization=1,
symmetric_l1_regularization=0,
loss_type='logistic_loss')
lr = SdcaModel(CONTAINER, examples, variables, options)
tf.initialize_all_variables().run()
unregularized_loss = lr.unregularized_loss(examples)
loss = lr.regularized_loss(examples)
predictions = lr.predictions(examples)
for _ in xrange(5):
lr.minimize().run()
self.assertAllClose(0.284860, unregularized_loss.eval(), rtol=0.08)
self.assertAllClose(0.408044, loss.eval(), atol=0.012)
predicted_labels = get_binary_predictions_for_logistic(predictions)
self.assertAllEqual([0, 1], predicted_labels.eval())
self.assertAllClose(0.01,
lr.approximate_duality_gap().eval(),
rtol=1e-2,
atol=1e-2)
def testSimple(self):
# Setup test data
example_protos = [
make_example_proto(
{'age': [0],
'gender': [0]}, -10.0),
make_example_proto(
{'age': [1],
'gender': [1]}, 14.0),
]
example_weights = [1.0, 1.0]
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(symmetric_l2_regularization=1,
symmetric_l1_regularization=0,
loss_type='squared_loss')
lr = SdcaModel(CONTAINER, examples, variables, options)
tf.initialize_all_variables().run()
predictions = lr.predictions(examples)
for _ in xrange(20):
lr.minimize().run()
# Predictions should be 2/3 of label due to minimizing regularized loss:
# (label - 2 * weight)^2 / 2 + L2 * 2 * weight^2
self.assertAllClose([-20.0 / 3.0, 28.0 / 3.0],
predictions.eval(),
rtol=0.005)
self.assertAllClose(0.01,
lr.approximate_duality_gap().eval(),
rtol=1e-2,
atol=1e-2)
def testSimple(self):
# Setup test data
example_protos = [
make_example_proto({"age": [0], "gender": [0]}, 0),
make_example_proto({"age": [1], "gender": [1]}, 1),
]
example_weights = [1.0, 1.0]
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(symmetric_l2_regularization=1, symmetric_l1_regularization=0, loss_type="logistic_loss")
lr = SdcaModel(CONTAINER, examples, variables, options)
tf.initialize_all_variables().run()
unregularized_loss = lr.unregularized_loss(examples)
loss = lr.regularized_loss(examples)
predictions = lr.predictions(examples)
self.assertAllClose(0.693147, unregularized_loss.eval())
self.assertAllClose(0.693147, loss.eval())
train_op = lr.minimize()
for _ in xrange(_MAX_ITERATIONS):
train_op.run()
# The high tolerance in unregularized_loss comparisons is due to the
# fact that it's possible to trade off unregularized_loss vs.
# regularization and still have a sum that is quite close to the
# optimal regularized_loss value. SDCA's duality gap only ensures that
# the regularized_loss is within 0.01 of optimal.
# 0.525457 is the optimal regularized_loss.
# 0.411608 is the unregularized_loss at that optimum.
self.assertAllClose(0.411608, unregularized_loss.eval(), atol=0.05)
self.assertAllClose(0.525457, loss.eval(), atol=0.01)
predicted_labels = get_binary_predictions_for_logistic(predictions)
self.assertAllEqual([0, 1], predicted_labels.eval())
self.assertAllClose(0.01, lr.approximate_duality_gap().eval(), rtol=1e-2, atol=1e-2)
def testSparseRandom(self):
dim = 20
num_examples = 1000
# Number of non-zero features per example.
non_zeros = 10
# Setup test data.
with self._single_threaded_test_session():
examples, variables = make_random_examples_and_variables_dicts(
num_examples, dim, non_zeros)
options = dict(
symmetric_l2_regularization=.1,
symmetric_l1_regularization=0,
num_table_shards=1,
adaptive=False,
loss_type='logistic_loss')
lr = SdcaModel(examples, variables, options)
variables_lib.global_variables_initializer().run()
train_op = lr.minimize()
for _ in range(4):
train_op.run()
lr.update_weights(train_op).run()
# Duality gap is 1.4e-5.
# It would be 0.01 without shuffling and 0.02 with adaptive sampling.
self.assertNear(0.0, lr.approximate_duality_gap().eval(), err=1e-3)
def testInstancesOfOneClassOnly(self):
# Setup test data with 1 positive (ignored), and 1 negative example.
example_protos = [
make_example_proto({
'age': [0],
'gender': [0]
}, 0),
make_example_proto({
'age': [1],
'gender': [0]
}, 1), # Shares gender with the instance above.
]
example_weights = [1.0, 0.0] # Second example "omitted" from training.
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(symmetric_l2_regularization=1,
symmetric_l1_regularization=0,
loss_type='logistic_loss')
lr = SdcaModel(CONTAINER, examples, variables, options)
tf.initialize_all_variables().run()
unregularized_loss = lr.unregularized_loss(examples)
loss = lr.regularized_loss(examples)
predictions = lr.predictions(examples)
for _ in xrange(5):
lr.minimize().run()
self.assertAllClose(0.411608, unregularized_loss.eval(), rtol=0.12)
self.assertAllClose(0.525457, loss.eval(), atol=0.01)
predicted_labels = get_binary_predictions_for_logistic(predictions)
self.assertAllEqual([0, 0], predicted_labels.eval())
self.assertAllClose(0.01,
lr.approximate_duality_gap().eval(),
rtol=1e-2,
atol=1e-2)
def testImbalancedWithExampleWeights(self):
# Setup test data with 1 positive, and 1 negative example.
example_protos = [
make_example_proto({"age": [0], "gender": [0]}, 0),
make_example_proto({"age": [1], "gender": [1]}, 1),
]
example_weights = [3.0, 1.0]
for num_shards in _SHARD_NUMBERS:
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(
symmetric_l2_regularization=1,
symmetric_l1_regularization=0,
num_table_shards=num_shards,
loss_type="logistic_loss",
)
lr = SdcaModel(examples, variables, options)
tf.initialize_all_variables().run()
unregularized_loss = lr.unregularized_loss(examples)
loss = lr.regularized_loss(examples)
predictions = lr.predictions(examples)
train_op = lr.minimize()
for _ in range(_MAX_ITERATIONS):
train_op.run()
self.assertAllClose(0.284860, unregularized_loss.eval(), atol=0.08)
self.assertAllClose(0.408044, loss.eval(), atol=0.012)
predicted_labels = get_binary_predictions_for_logistic(predictions)
self.assertAllEqual([0, 1], predicted_labels.eval())
self.assertAllClose(0.0, lr.approximate_duality_gap().eval(), rtol=2e-2, atol=1e-2)
def testInstancesOfOneClassOnly(self):
# Setup test data with 1 positive (ignored), and 1 negative example.
example_protos = [
make_example_proto(
{'age': [0],
'gender': [0]}, 0),
make_example_proto(
{'age': [1],
'gender': [0]}, 1), # Shares gender with the instance above.
]
example_weights = [1.0, 0.0] # Second example "omitted" from training.
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(symmetric_l2_regularization=1,
symmetric_l1_regularization=0,
loss_type='logistic_loss')
lr = SdcaModel(CONTAINER, examples, variables, options)
tf.initialize_all_variables().run()
unregularized_loss = lr.unregularized_loss(examples)
loss = lr.regularized_loss(examples)
predictions = lr.predictions(examples)
for _ in xrange(5):
lr.minimize().run()
self.assertAllClose(0.411608, unregularized_loss.eval(), rtol=0.12)
self.assertAllClose(0.525457, loss.eval(), atol=0.01)
predicted_labels = get_binary_predictions_for_logistic(predictions)
self.assertAllEqual([0, 0], predicted_labels.eval())
self.assertAllClose(0.01,
lr.approximate_duality_gap().eval(),
rtol=1e-2,
atol=1e-2)
def testImbalancedWithExampleWeights(self):
# Setup test data with 1 positive, and 1 negative example.
example_protos = [
make_example_proto(
{'age': [0],
'gender': [0]}, 0),
make_example_proto(
{'age': [1],
'gender': [1]}, 1),
]
example_weights = [3.0, 1.0]
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(symmetric_l2_regularization=1,
symmetric_l1_regularization=0,
loss_type='logistic_loss')
lr = SdcaModel(CONTAINER, examples, variables, options)
tf.initialize_all_variables().run()
unregularized_loss = lr.unregularized_loss(examples)
loss = lr.regularized_loss(examples)
predictions = lr.predictions(examples)
for _ in xrange(5):
lr.minimize().run()
self.assertAllClose(0.284860, unregularized_loss.eval(), rtol=0.08)
self.assertAllClose(0.408044, loss.eval(), atol=0.012)
predicted_labels = get_binary_predictions_for_logistic(predictions)
self.assertAllEqual([0, 1], predicted_labels.eval())
self.assertAllClose(0.01,
lr.approximate_duality_gap().eval(),
rtol=1e-2,
atol=1e-2)
def testInstancesOfOneClassOnly(self):
# Setup test data with 1 positive (ignored), and 1 negative example.
example_protos = [
make_example_proto({"age": [0], "gender": [0]}, 0),
make_example_proto({"age": [1], "gender": [0]}, 1), # Shares gender with the instance above.
]
example_weights = [1.0, 0.0] # Second example "omitted" from training.
for num_shards in _SHARD_NUMBERS:
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(
symmetric_l2_regularization=1,
symmetric_l1_regularization=0,
num_table_shards=num_shards,
loss_type="logistic_loss",
)
lr = SdcaModel(examples, variables, options)
tf.initialize_all_variables().run()
unregularized_loss = lr.unregularized_loss(examples)
loss = lr.regularized_loss(examples)
predictions = lr.predictions(examples)
train_op = lr.minimize()
for _ in range(_MAX_ITERATIONS):
train_op.run()
self.assertAllClose(0.411608, unregularized_loss.eval(), atol=0.05)
self.assertAllClose(0.525457, loss.eval(), atol=0.01)
predicted_labels = get_binary_predictions_for_logistic(predictions)
self.assertAllEqual([0, 0], predicted_labels.eval())
self.assertAllClose(0.01, lr.approximate_duality_gap().eval(), rtol=1e-2, atol=1e-2)
def testSomeUnweightedExamples(self):
# Setup test data with 4 examples, but should produce the same
# results as testSimple.
example_protos = [
# Will be used.
make_example_proto({
'age': [0],
'gender': [0]
}, 0),
# Will be ignored.
make_example_proto({
'age': [1],
'gender': [0]
}, 0),
# Will be used.
make_example_proto({
'age': [1],
'gender': [1]
}, 1),
# Will be ignored.
make_example_proto({
'age': [1],
'gender': [0]
}, 1),
]
example_weights = [1.0, 0.0, 1.0, 0.0]
for num_shards in _SHARD_NUMBERS:
with self._single_threaded_test_session():
# Only use examples 0 and 2
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(symmetric_l2_regularization=1,
symmetric_l1_regularization=0,
loss_type='logistic_loss')
lr = SdcaModel(CONTAINER,
examples,
variables,
options,
num_table_shards=num_shards)
tf.initialize_all_variables().run()
unregularized_loss = lr.unregularized_loss(examples)
loss = lr.regularized_loss(examples)
predictions = lr.predictions(examples)
train_op = lr.minimize()
for _ in range(_MAX_ITERATIONS):
train_op.run()
self.assertAllClose(0.411608,
unregularized_loss.eval(),
atol=0.05)
self.assertAllClose(0.525457, loss.eval(), atol=0.01)
predicted_labels = get_binary_predictions_for_logistic(
predictions)
self.assertAllClose([0, 1, 1, 1], predicted_labels.eval())
self.assertAllClose(0.01,
lr.approximate_duality_gap().eval(),
rtol=1e-2,
atol=1e-2)
def testDistributedSimple(self):
# Setup test data
example_protos = [
make_example_proto({'age': [0],
'gender': [0]}, 0),
make_example_proto({'age': [1],
'gender': [1]}, 1),
]
example_weights = [1.0, 1.0]
for num_shards in _SHARD_NUMBERS:
for num_loss_partitions in _NUM_LOSS_PARTITIONS:
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(
symmetric_l2_regularization=1,
symmetric_l1_regularization=0,
loss_type='logistic_loss',
num_table_shards=num_shards,
num_loss_partitions=num_loss_partitions)
lr = SdcaModel(examples, variables, options)
tf.initialize_all_variables().run()
unregularized_loss = lr.unregularized_loss(examples)
loss = lr.regularized_loss(examples)
predictions = lr.predictions(examples)
self.assertAllClose(0.693147, unregularized_loss.eval())
self.assertAllClose(0.693147, loss.eval())
train_op = lr.minimize()
def Minimize():
with self._single_threaded_test_session():
for _ in range(_MAX_ITERATIONS):
train_op.run()
threads = []
for _ in range(num_loss_partitions):
threads.append(Thread(target=Minimize))
threads[-1].start()
for t in threads:
t.join()
lr.update_weights(train_op).run()
# The high tolerance in unregularized_loss comparisons is due to the
# fact that it's possible to trade off unregularized_loss vs.
# regularization and still have a sum that is quite close to the
# optimal regularized_loss value. SDCA's duality gap only ensures
# that the regularized_loss is within 0.01 of optimal.
# 0.525457 is the optimal regularized_loss.
# 0.411608 is the unregularized_loss at that optimum.
self.assertAllClose(0.411608, unregularized_loss.eval(), atol=0.05)
self.assertAllClose(0.525457, loss.eval(), atol=0.01)
predicted_labels = get_binary_predictions_for_logistic(predictions)
self.assertAllEqual([0, 1], predicted_labels.eval())
self.assertTrue(lr.approximate_duality_gap().eval() < 0.02)
def testDistributedSimple(self):
# Setup test data
example_protos = [
make_example_proto({'age': [0],
'gender': [0]}, 0),
make_example_proto({'age': [1],
'gender': [1]}, 1),
]
example_weights = [1.0, 1.0]
for num_shards in _SHARD_NUMBERS:
for num_loss_partitions in _NUM_LOSS_PARTITIONS:
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(
symmetric_l2_regularization=1,
symmetric_l1_regularization=0,
loss_type='logistic_loss',
num_table_shards=num_shards,
num_loss_partitions=num_loss_partitions)
lr = SdcaModel(examples, variables, options)
tf.global_variables_initializer().run()
unregularized_loss = lr.unregularized_loss(examples)
loss = lr.regularized_loss(examples)
predictions = lr.predictions(examples)
self.assertAllClose(0.693147, unregularized_loss.eval())
self.assertAllClose(0.693147, loss.eval())
train_op = lr.minimize()
def Minimize():
with self._single_threaded_test_session():
for _ in range(_MAX_ITERATIONS):
train_op.run()
threads = []
for _ in range(num_loss_partitions):
threads.append(Thread(target=Minimize))
threads[-1].start()
for t in threads:
t.join()
lr.update_weights(train_op).run()
# The high tolerance in unregularized_loss comparisons is due to the
# fact that it's possible to trade off unregularized_loss vs.
# regularization and still have a sum that is quite close to the
# optimal regularized_loss value. SDCA's duality gap only ensures
# that the regularized_loss is within 0.01 of optimal.
# 0.525457 is the optimal regularized_loss.
# 0.411608 is the unregularized_loss at that optimum.
self.assertAllClose(0.411608, unregularized_loss.eval(), atol=0.05)
self.assertAllClose(0.525457, loss.eval(), atol=0.01)
predicted_labels = get_binary_predictions_for_logistic(predictions)
self.assertAllEqual([0, 1], predicted_labels.eval())
self.assertTrue(lr.approximate_duality_gap().eval() < 0.02)
def testImbalanced(self):
# Setup test data with 1 positive, and 3 negative examples.
example_protos = [
make_example_proto({
'age': [0],
'gender': [0]
}, 0),
make_example_proto({
'age': [2],
'gender': [0]
}, 0),
make_example_proto({
'age': [3],
'gender': [0]
}, 0),
make_example_proto({
'age': [1],
'gender': [1]
}, 1),
]
example_weights = [1.0, 1.0, 1.0, 1.0]
for num_shards in _SHARD_NUMBERS:
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(3, 1)
options = dict(symmetric_l2_regularization=1,
symmetric_l1_regularization=0,
loss_type='logistic_loss')
lr = SdcaModel(CONTAINER,
examples,
variables,
options,
num_table_shards=num_shards)
tf.initialize_all_variables().run()
unregularized_loss = lr.unregularized_loss(examples)
loss = lr.regularized_loss(examples)
predictions = lr.predictions(examples)
train_op = lr.minimize()
for _ in range(_MAX_ITERATIONS):
train_op.run()
self.assertAllClose(0.226487 + 0.102902,
unregularized_loss.eval(),
atol=0.08)
self.assertAllClose(0.328394 + 0.131364,
loss.eval(),
atol=0.01)
predicted_labels = get_binary_predictions_for_logistic(
predictions)
self.assertAllEqual([0, 0, 0, 1], predicted_labels.eval())
self.assertAllClose(0.01,
lr.approximate_duality_gap().eval(),
rtol=1e-2,
atol=1e-2)
def testSimpleNoL2(self):
# Same as test above (so comments from above apply) but without an L2.
# The algorithm should behave as if we have an L2 of 1 in optimization but
# 0 in regularized_loss.
example_protos = [
make_example_proto({
'age': [0],
'gender': [0]
}, 0),
make_example_proto({
'age': [1],
'gender': [1]
}, 1),
]
example_weights = [1.0, 1.0]
for num_shards in _SHARD_NUMBERS:
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(symmetric_l2_regularization=0,
symmetric_l1_regularization=0,
loss_type='logistic_loss')
lr = SdcaModel(CONTAINER,
examples,
variables,
options,
num_table_shards=num_shards)
tf.initialize_all_variables().run()
unregularized_loss = lr.unregularized_loss(examples)
loss = lr.regularized_loss(examples)
predictions = lr.predictions(examples)
self.assertAllClose(0.693147, unregularized_loss.eval())
self.assertAllClose(0.693147, loss.eval())
train_op = lr.minimize()
for _ in range(_MAX_ITERATIONS):
train_op.run()
# There is neither L1 nor L2 loss, so regularized and unregularized
# losses should be exactly the same.
self.assertAllClose(0.40244,
unregularized_loss.eval(),
atol=0.01)
self.assertAllClose(0.40244, loss.eval(), atol=0.01)
predicted_labels = get_binary_predictions_for_logistic(
predictions)
self.assertAllEqual([0, 1], predicted_labels.eval())
self.assertAllClose(0.01,
lr.approximate_duality_gap().eval(),
rtol=1e-2,
atol=1e-2)
def testImbalanced(self):
# Setup test data with 1 positive, and 3 negative examples.
example_protos = [
make_example_proto({
'age': [0],
'gender': [0]
}, 0),
make_example_proto({
'age': [2],
'gender': [0]
}, 0),
make_example_proto({
'age': [3],
'gender': [0]
}, 0),
make_example_proto({
'age': [1],
'gender': [1]
}, 1),
]
example_weights = [1.0, 1.0, 1.0, 1.0]
for num_shards in _SHARD_NUMBERS:
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(3, 1)
options = dict(
symmetric_l2_regularization=1,
symmetric_l1_regularization=0,
num_table_shards=num_shards,
loss_type='logistic_loss')
lr = SdcaModel(examples, variables, options)
variables_lib.global_variables_initializer().run()
unregularized_loss = lr.unregularized_loss(examples)
loss = lr.regularized_loss(examples)
predictions = lr.predictions(examples)
train_op = lr.minimize()
for _ in range(_MAX_ITERATIONS):
train_op.run()
lr.update_weights(train_op).run()
self.assertAllClose(
0.226487 + 0.102902, unregularized_loss.eval(), atol=0.08)
self.assertAllClose(0.328394 + 0.131364, loss.eval(), atol=0.01)
predicted_labels = get_binary_predictions_for_logistic(predictions)
self.assertAllEqual([0, 0, 0, 1], predicted_labels.eval())
self.assertAllClose(
0.0, lr.approximate_duality_gap().eval(), rtol=2e-2, atol=1e-2)
def testPartitionedPrimals(self):
# Setup test data
example_protos = [
make_example_proto({
'age': [0],
'gender': [0]
}, 0),
make_example_proto({
'age': [1],
'gender': [1]
}, 1),
]
example_weights = [1.0, 1.0]
for num_shards in _SHARD_NUMBERS:
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1, partitioned=True)
options = dict(
symmetric_l2_regularization=1,
symmetric_l1_regularization=0,
num_table_shards=num_shards,
loss_type='logistic_loss')
lr = SdcaModel(examples, variables, options)
variables_lib.global_variables_initializer().run()
unregularized_loss = lr.unregularized_loss(examples)
loss = lr.regularized_loss(examples)
predictions = lr.predictions(examples)
self.assertAllClose(0.693147, unregularized_loss.eval())
self.assertAllClose(0.693147, loss.eval())
train_op = lr.minimize()
for _ in range(_MAX_ITERATIONS):
train_op.run()
lr.update_weights(train_op).run()
# The high tolerance in unregularized_loss comparisons is due to the
# fact that it's possible to trade off unregularized_loss vs.
# regularization and still have a sum that is quite close to the
# optimal regularized_loss value. SDCA's duality gap only ensures that
# the regularized_loss is within 0.01 of optimal.
# 0.525457 is the optimal regularized_loss.
# 0.411608 is the unregularized_loss at that optimum.
self.assertAllClose(0.411608, unregularized_loss.eval(), atol=0.05)
self.assertAllClose(0.525457, loss.eval(), atol=0.01)
predicted_labels = get_binary_predictions_for_logistic(predictions)
self.assertAllEqual([0, 1], predicted_labels.eval())
self.assertAllClose(
0.01, lr.approximate_duality_gap().eval(), rtol=1e-2, atol=1e-2)
def testSimple(self):
# Setup test data
example_protos = [
make_example_proto({
'age': [0],
'gender': [0]
}, 0),
make_example_proto({
'age': [1],
'gender': [1]
}, 2),
]
example_weights = [100.0, 100.0]
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(
symmetric_l2_regularization=1.0,
symmetric_l1_regularization=0,
loss_type='poisson_loss')
model = SdcaModel(examples, variables, options)
variables_lib.global_variables_initializer().run()
# Before minimization, the weights default to zero. There is no loss due
# to regularization, only unregularized loss which is 1 for each example.
predictions = model.predictions(examples)
self.assertAllClose([1.0, 1.0], predictions.eval())
unregularized_loss = model.unregularized_loss(examples)
regularized_loss = model.regularized_loss(examples)
approximate_duality_gap = model.approximate_duality_gap()
self.assertAllClose(1.0, unregularized_loss.eval())
self.assertAllClose(1.0, regularized_loss.eval())
# There are 4 sparse weights: 2 for age (say w1, w2) and 2 for gender
# (say w3 and w4). The minimization leads to:
# w1=w3=-1.96487, argmin of 100*(exp(2*w)-2*w*0)+w**2.
# w2=w4=0.345708, argmin of 100*(exp(2*w)-2*w*2)+w**2.
# This gives an unregularized loss of .3167 and .3366 with regularization.
train_op = model.minimize()
for _ in range(_MAX_ITERATIONS):
train_op.run()
model.update_weights(train_op).run()
self.assertAllClose([0.0196, 1.9965], predictions.eval(), atol=1e-4)
self.assertAllClose(0.3167, unregularized_loss.eval(), atol=1e-4)
self.assertAllClose(0.3366, regularized_loss.eval(), atol=1e-4)
self.assertAllClose(0., approximate_duality_gap.eval(), atol=1e-6)
def testSimpleLogistic(self):
# Setup test data
example_protos = [
make_example_proto({
'age': [0],
'gender': [0]
}, 0),
make_example_proto({
'age': [1],
'gender': [1]
}, 1),
]
example_weights = [1.0, 1.0]
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(symmetric_l2_regularization=1,
symmetric_l1_regularization=0,
loss_type='logistic_loss')
lr = SdcaModel(CONTAINER, examples, variables, options)
tf.initialize_all_variables().run()
unregularized_loss = lr.unregularized_loss(examples)
loss = lr.regularized_loss(examples)
predictions = lr.predictions(examples)
self.assertAllClose(0.693147, unregularized_loss.eval())
self.assertAllClose(0.693147, loss.eval())
for _ in xrange(5):
lr.minimize().run()
# The high tolerance in unregularized_loss comparisons is due to the
# fact that it's possible to trade off unregularized_loss vs.
# regularization and still have a sum that is quite close to the
# optimal regularized_loss value. SDCA's duality gap only ensures that
# the regularized_loss is within 0.01 of optimal.
# 0.525457 is the optimal regularized_loss.
# 0.411608 is the unregularized_loss at that optimum.
self.assertAllClose(0.411608, unregularized_loss.eval(), rtol=0.11)
self.assertAllClose(0.525457, loss.eval(), atol=0.01)
predicted_labels = get_binary_predictions_for_logistic(predictions)
self.assertAllEqual([0, 1], predicted_labels.eval())
self.assertAllClose(0.01,
lr.approximate_duality_gap().eval(),
rtol=1e-2,
atol=1e-2)
def testImbalancedWithExampleWeights(self):
# Setup test data with 1 positive, and 1 negative example.
example_protos = [
make_example_proto({
'age': [0],
'gender': [0]
}, 0),
make_example_proto({
'age': [1],
'gender': [1]
}, 1),
]
example_weights = [3.0, 1.0]
for num_shards in _SHARD_NUMBERS:
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(symmetric_l2_regularization=1,
symmetric_l1_regularization=0,
num_table_shards=num_shards,
loss_type='logistic_loss')
lr = SdcaModel(examples, variables, options)
variables_lib.global_variables_initializer().run()
unregularized_loss = lr.unregularized_loss(examples)
loss = lr.regularized_loss(examples)
predictions = lr.predictions(examples)
train_op = lr.minimize()
for _ in range(_MAX_ITERATIONS):
train_op.run()
lr.update_weights(train_op).run()
self.assertAllClose(0.284860,
unregularized_loss.eval(),
atol=0.08)
self.assertAllClose(0.408044, loss.eval(), atol=0.012)
predicted_labels = get_binary_predictions_for_logistic(
predictions)
self.assertAllEqual([0, 1], predicted_labels.eval())
self.assertAllClose(0.0,
lr.approximate_duality_gap().eval(),
rtol=2e-2,
atol=1e-2)
def testInstancesOfOneClassOnly(self):
# Setup test data with 1 positive (ignored), and 1 negative example.
example_protos = [
make_example_proto({
'age': [0],
'gender': [0]
}, 0),
make_example_proto({
'age': [1],
'gender': [0]
}, 1), # Shares gender with the instance above.
]
example_weights = [1.0, 0.0] # Second example "omitted" from training.
for num_shards in _SHARD_NUMBERS:
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(symmetric_l2_regularization=1,
symmetric_l1_regularization=0,
num_table_shards=num_shards,
loss_type='logistic_loss')
lr = SdcaModel(examples, variables, options)
variables_lib.global_variables_initializer().run()
unregularized_loss = lr.unregularized_loss(examples)
loss = lr.regularized_loss(examples)
predictions = lr.predictions(examples)
train_op = lr.minimize()
for _ in range(_MAX_ITERATIONS):
train_op.run()
lr.update_weights(train_op).run()
self.assertAllClose(0.411608,
unregularized_loss.eval(),
atol=0.05)
self.assertAllClose(0.525457, loss.eval(), atol=0.01)
predicted_labels = get_binary_predictions_for_logistic(
predictions)
self.assertAllEqual([0, 0], predicted_labels.eval())
self.assertAllClose(0.01,
lr.approximate_duality_gap().eval(),
rtol=1e-2,
atol=1e-2)
def testSimpleLogisticNoL2(self):
# Same as test above (so comments from above apply) but without an L2.
# The algorithm should behave as if we have an L2 of 1 in optimization but
# 0 in regularized_loss.
example_protos = [
make_example_proto({
'age': [0],
'gender': [0]
}, 0),
make_example_proto({
'age': [1],
'gender': [1]
}, 1),
]
example_weights = [1.0, 1.0]
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(symmetric_l2_regularization=0,
symmetric_l1_regularization=0,
loss_type='logistic_loss')
lr = SdcaModel(CONTAINER, examples, variables, options)
tf.initialize_all_variables().run()
unregularized_loss = lr.unregularized_loss(examples)
loss = lr.regularized_loss(examples)
predictions = lr.predictions(examples)
self.assertAllClose(0.693147, unregularized_loss.eval())
self.assertAllClose(0.693147, loss.eval())
for _ in xrange(5):
lr.minimize().run()
self.assertAllClose(0.411608, unregularized_loss.eval(), rtol=0.11)
self.assertAllClose(0.371705, loss.eval(), atol=0.01)
predicted_labels = get_binary_predictions_for_logistic(predictions)
self.assertAllEqual([0, 1], predicted_labels.eval())
self.assertAllClose(0.01,
lr.approximate_duality_gap().eval(),
rtol=1e-2,
atol=1e-2)
def testSimple(self):
# Setup test data
example_protos = [
make_example_proto({
'age': [0],
'gender': [0]
}, -10.0),
make_example_proto({
'age': [1],
'gender': [1]
}, 14.0),
]
example_weights = [1.0, 1.0]
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(symmetric_l2_regularization=1,
symmetric_l1_regularization=0,
loss_type='squared_loss')
lr = SdcaModel(examples, variables, options)
variables_lib.global_variables_initializer().run()
predictions = lr.predictions(examples)
train_op = lr.minimize()
for _ in range(_MAX_ITERATIONS):
train_op.run()
lr.update_weights(train_op).run()
# Predictions should be 2/3 of label due to minimizing regularized loss:
# (label - 2 * weight)^2 / 2 + L2 * 2 * weight^2
self.assertAllClose([-20.0 / 3.0, 28.0 / 3.0],
predictions.eval(),
rtol=0.005)
# Approximate gap should be very close to 0.0. (In fact, because the gap
# is only approximate, it is likely that upon convergence the duality gap
# can have a tiny negative value).
self.assertAllClose(0.0,
lr.approximate_duality_gap().eval(),
atol=1e-2)
def testSimpleNoL2(self):
# Same as test above (so comments from above apply) but without an L2.
# The algorithm should behave as if we have an L2 of 1 in optimization but
# 0 in regularized_loss.
example_protos = [
make_example_proto(
{'age': [0],
'gender': [0]}, 0),
make_example_proto(
{'age': [1],
'gender': [1]}, 1),
]
example_weights = [1.0, 1.0]
with self._single_threaded_test_session():
examples = make_example_dict(example_protos, example_weights)
variables = make_variable_dict(1, 1)
options = dict(symmetric_l2_regularization=0,
symmetric_l1_regularization=0,
loss_type='logistic_loss')
lr = SdcaModel(CONTAINER, examples, variables, options)
tf.initialize_all_variables().run()
unregularized_loss = lr.unregularized_loss(examples)
loss = lr.regularized_loss(examples)
predictions = lr.predictions(examples)
self.assertAllClose(0.693147, unregularized_loss.eval())
self.assertAllClose(0.693147, loss.eval())
for _ in xrange(5):
lr.minimize().run()
self.assertAllClose(0.411608, unregularized_loss.eval(), rtol=0.11)
self.assertAllClose(0.371705, loss.eval(), atol=0.01)
predicted_labels = get_binary_predictions_for_logistic(predictions)
self.assertAllEqual([0, 1], predicted_labels.eval())
self.assertAllClose(0.01,
lr.approximate_duality_gap().eval(),
rtol=1e-2,
atol=1e-2)
def testDistributedSimple(self):
# Distributed SDCA may not converge if the workers update concurrently the
# same example. In this test the examples are partitioned across workers.
# The examples are the same for all workers, just the example_ids are
# different.
example_protos = [
make_example_proto({
'age': [0],
'gender': [0]
}, 0),
make_example_proto({
'age': [1],
'gender': [1]
}, 1),
]
example_weights = [1.0, 1.0]
examples = make_example_dict(example_protos, example_weights)
example_ids = array_ops.placeholder(
dtypes.string, shape=(len(example_weights),))
examples['example_ids'] = example_ids
variables = make_variable_dict(1, 1)
for num_shards in _SHARD_NUMBERS:
for num_loss_partitions in _NUM_LOSS_PARTITIONS:
with self._single_threaded_test_session():
options = dict(
# Keep the same solution as for TestSimple: since the number of
# examples is multplied by num_loss_partitions, multiply also
# L2 by the same value.
symmetric_l2_regularization=num_loss_partitions,
symmetric_l1_regularization=0,
loss_type='logistic_loss',
num_table_shards=num_shards,
num_loss_partitions=num_loss_partitions)
lr = SdcaModel(examples, variables, options)
variables_lib.global_variables_initializer().run()
unregularized_loss = lr.unregularized_loss(examples)
loss = lr.regularized_loss(examples)
predictions = lr.predictions(examples)
self.assertAllClose(0.693147, unregularized_loss.eval())
self.assertAllClose(0.693147, loss.eval())
train_op = lr.minimize()
def minimize(worker_id):
with self._single_threaded_test_session():
feed_dict = {example_ids: [
str(i + worker_id*len(example_weights)) for i in range(
len(example_weights))]}
for _ in range(_MAX_ITERATIONS):
train_op.run(feed_dict=feed_dict) # pylint: disable=cell-var-from-loop
threads = []
for worker_id in range(num_loss_partitions):
threads.append(threading.Thread(target=minimize, args=(worker_id,)))
threads[-1].start()
for t in threads:
t.join()
lr.update_weights(train_op).run(feed_dict={
example_ids: [str(i) for i in range(len(example_weights))]})
# Test only the unregularized loss because the optimal value of the
# regularized loss depends on num_loss_partitions.
self.assertAllClose(0.411608, unregularized_loss.eval(), atol=0.02)
predicted_labels = get_binary_predictions_for_logistic(predictions)
self.assertAllEqual([0, 1], predicted_labels.eval())
self.assertNear(0.0, lr.approximate_duality_gap().eval(), 0.02)
