def mnist8m_experiment(method,
components,
sparsity_factor,
run_id,
image=None,
n_threads=1,
partition_size=3000,
optimize_stochastic=True,
num_samples=1000,
max_iter=8000):
"""
Run the mnist8m experiment.
Parameters
----------
method : str
The method under which to run the experiment (mix1, mix2, or full).
sparsity_factor : float
The sparsity of inducing points.
run_id : int
The id of the configuration.
"""
name = 'mnist8m'
data = data_source.mnist8m_data()[run_id - 1]
kernel = [
ExtRBF(data['train_inputs'].shape[1],
variance=11,
lengthscale=np.array((9., )),
ARD=False) for _ in range(10)
]
cond_ll = likelihood.SoftmaxLL(10)
transform = data_transformation.IdentityTransformation(
data['train_inputs'], data['train_outputs'])
return run_model.run_model(data['train_inputs'],
data['train_outputs'],
data['test_inputs'],
data['test_outputs'],
cond_ll,
kernel,
method,
components,
name,
data['id'],
sparsity_factor,
transform,
False,
False,
optimization_config={
'mog': 60,
'hyp': 15
},
num_samples=num_samples,
max_iter=max_iter,
n_threads=n_threads,
ftol=10,
model_image_dir=image,
partition_size=partition_size,
optimize_stochastic=optimize_stochastic)
def mnist_binary_inducing_experiment(method,
sparsity_factor,
run_id,
image=None,
n_threads=1,
partition_size=3000,
optimize_stochastic=False):
"""
Run the binary mnist experiment with inducing point learning.
Parameters
----------
method : str
The method under which to run the experiment (mix1, mix2, or full).
sparsity_factor : float
The sparsity of inducing points.
run_id : int
The id of the configuration.
"""
name = 'mnist_binary'
data = data_source.mnist_binary_data()[run_id - 1]
kernel = [
ExtRBF(data['train_inputs'].shape[1],
variance=11,
lengthscale=np.array((9., )),
ARD=False)
]
cond_ll = likelihood.LogisticLL()
transform = data_transformation.IdentityTransformation(
data['train_inputs'], data['train_outputs'])
return run_model.run_model(data['train_inputs'],
data['train_outputs'],
data['test_inputs'],
data['test_outputs'],
cond_ll,
kernel,
method,
name,
data['id'],
sparsity_factor,
transform,
False,
False,
optimization_config={
'mog': 60,
'hyp': 15,
'inducing': 6
},
max_iter=9,
n_threads=n_threads,
ftol=10,
model_image_dir=image,
partition_size=partition_size,
optimize_stochastic=optimize_stochastic)
def usps_experiment(method,
components,
sparsity_factor,
run_id,
optimize_stochastic=False):
"""
Run the usps experiment.
Parameters
----------
method : str
The method under which to run the experiment (mix1, mix2, or full).
sparsity_factor : float
The sparsity of inducing points.
run_id : int
The id of the configuration.
"""
name = 'usps'
data = data_source.usps_data()[run_id - 1]
kernel = [
ExtRBF(data['train_inputs'].shape[1],
variance=2,
lengthscale=np.array((4., )),
ARD=False) for _ in range(3)
]
cond_ll = likelihood.SoftmaxLL(3)
transform = data_transformation.IdentityTransformation(
data['train_inputs'], data['train_outputs'])
return run_model.run_model(data['train_inputs'],
data['train_outputs'],
data['test_inputs'],
data['test_outputs'],
cond_ll,
kernel,
method,
components,
name,
data['id'],
sparsity_factor,
transform,
True,
False,
optimization_config={
'mog': 25,
'hyp': 25
},
max_iter=300)
def wisconsin_experiment(method,
components,
sparsity_factor,
run_id,
optimize_stochastic=False):
"""
Run the wisconsin experiment.
Parameters
----------
method : str
The method under which to run the experiment (mix1, mix2, or full).
sparsity_factor : float
The sparsity of inducing points.
run_id : int
The id of the configuration.
"""
name = 'breast_cancer'
data = data_source.wisconsin_breast_cancer_data()[run_id - 1]
kernel = get_kernels(data['train_inputs'].shape[1], 1, False)
cond_ll = likelihood.LogisticLL()
transform = data_transformation.IdentityTransformation(
data['train_inputs'], data['train_outputs'])
return run_model.run_model(data['train_inputs'],
data['train_outputs'],
data['test_inputs'],
data['test_outputs'],
cond_ll,
kernel,
method,
components,
name,
data['id'],
sparsity_factor,
transform,
True,
False,
optimization_config={
'mog': 25,
'hyp': 25
},
max_iter=200)
def mining_experiment(method,
components,
sparsity_factor,
run_id,
optimize_stochastic=False):
"""
Run the mining experiment.
Parameters
----------
method : str
The method under which to run the experiment (mix1, mix2, or full).
sparsity_factor : float
The sparsity of inducing points.
run_id : int
The id of the configuration.
"""
name = 'mining'
data = data_source.mining_data()[run_id - 1]
kernel = get_kernels(data['train_inputs'].shape[1], 1, False)
cond_ll = likelihood.LogGaussianCox(np.log(191. / 811))
transform = data_transformation.IdentityTransformation(
data['train_inputs'], data['train_outputs'])
kernel[0].variance = 1.0
kernel[0].lengthscale = 13516.0
return run_model.run_model(data['train_inputs'],
data['train_outputs'],
data['test_inputs'],
data['test_outputs'],
cond_ll,
kernel,
method,
components,
name,
data['id'],
sparsity_factor,
transform,
True,
True,
optimization_config={'mog': 15000},
max_iter=1)
def seismic_experiment(method,
components,
sparsity_factor,
run_id,
image=None,
n_threads=1,
partition_size=3000,
optimize_stochastic=False):
name = 'seismic'
data = data_source.seismic_data()[0]
# prior_var = np.array([900, 5625, 57600, 108900, 38025, 52900, 75625, 133225])
# prior_mu = [200, 500, 1600, 2200, 1950, 2300, 2750, 3650]
# sigma2y = [0.0006, 0.0025, 0.0056, 0.0100]
scale_factor = 10. # for numerical reasons (final predicitons to be post-processed)
mean_depth = np.array([200.0, 500.0, 1600.0, 2200.0], dtype=np.double)
mean_vel = np.array([1950.0, 2300.0, 2750.0, 3650.0], dtype=np.double)
std_depth = mean_depth * 0.15
std_vel = mean_vel * 0.10
prior_mu = np.hstack((mean_depth, mean_vel)) / scale_factor
prior_var = np.square(np.hstack(
(std_depth, std_vel))) / (scale_factor * scale_factor)
sigma2y = np.square([0.025, 0.05, 0.075, 0.1])
input_dim = data['train_inputs'].shape[1]
kernel = [
ExtRBF(input_dim,
variance=prior_var[i],
lengthscale=np.array((1, )),
ARD=True) for i in range(len(prior_var))
]
cond_ll = likelihood.SeismicLL(4, sigma2y)
transform = data_transformation.IdentityTransformation(
data['train_inputs'], data['train_outputs'])
#transform = data_transformation.MeanStdXTransformation(data['train_inputs'], data['train_outputs'])
return run_model.run_model(
data['train_inputs'],
data['train_outputs'],
data['test_inputs'],
data['test_outputs'],
cond_ll,
kernel,
method,
components,
name,
data['id'],
sparsity_factor,
transform,
False,
True,
optimization_config={'mog': 100},
# max_iter=10,
partition_size=partition_size,
# ftol=1,
n_threads=n_threads,
model_image_dir=image,
GP_mean=prior_mu,
init_var=0.001 * prior_var,
num_samples=100000,
)