def benchmark_function(
function,
seed,
n_eval=20,
n_initial_points=5,
model_class=None,
model_kwargs=None,
):
lower = np.array([-10])
upper = np.array([10])
rng1 = np.random.RandomState(seed)
rng2 = np.random.RandomState(seed)
cov_amp = 2
n_dims = lower.shape[0]
initial_ls = np.ones([n_dims])
exp_kernel = george.kernels.Matern52Kernel(initial_ls,
ndim=n_dims)
kernel = cov_amp * exp_kernel
prior = DefaultPrior(len(kernel) + 1)
if model_class is None:
model = GaussianProcess(
kernel,
prior=prior,
rng=rng1,
normalize_output=True,
normalize_input=True,
lower=lower,
upper=upper,
noise=1e-3,
)
else:
model = model_class(rng=rng1, **model_kwargs)
acq = LogEI(model)
max_func = SciPyOptimizer(acq, lower, upper, n_restarts=50, rng=rng2)
bo = BayesianOptimization(
objective_func=function,
lower=np.array([-10]),
upper=np.array([10]),
acquisition_func=acq,
model=model,
initial_points=n_initial_points,
initial_design=init_latin_hypercube_sampling,
rng=rng2,
maximize_func=max_func
)
bo.run(n_eval)
rval = np.minimum.accumulate(bo.y)
return rval
def Gp(self, seed):
"""
Bayesian optimization with Gaussian process(mcmc)
"""
lower = np.zeros((self.x.shape[2]))
upper = np.ones((self.x.shape[2]))
inc = np.ones((self.T, 50))
for t in range(self.T):
rng = np.random.RandomState(seed) # this per task per random run
cov_amp = 2
n_dims = self.x.shape[2]
initial_ls = np.ones([n_dims])
exp_kernel = george.kernels.Matern52Kernel(initial_ls, ndim=n_dims)
kernel = cov_amp * exp_kernel
prior = DefaultPrior(len(kernel) + 1)
n_hypers = 3 * len(kernel)
if n_hypers % 2 == 1:
n_hypers += 1
model = GaussianProcess(kernel,
prior=prior,
rng=rng,
normalize_output=False,
normalize_input=False,
noise=1e-6)
acq = EI(model)
# for the initial design, initialize the class with x-task
f = Objective_function(self.x[t], self.y[t], self.metadata[t])
indes = InDesign(self.x[t])
randdes = Rand_Design(self.x[t])
max_func = RandomSampling(acq,
lower,
upper,
randdes,
n_samples=100,
rng=rng)
bo = BayesianOptimization(
f.call,
lower=lower,
upper=upper,
acquisition_func=acq,
model=model,
initial_design=randdes.initial_design_random,
initial_points=3,
rng=rng,
maximize_func=max_func)
bo.run(num_iterations=50)
inc[t] = bo.incumbents_values
return inc
def suggest_configuration(self):
if self.X is None and self.y is None:
new_x = init_random_uniform(self.lower, self.upper,
n_points=1, rng=self.rng)[0, :]
elif self.X.shape[0] == 1:
# We need at least 2 data points to train a GP
new_x = init_random_uniform(self.lower, self.upper,
n_points=1, rng=self.rng)[0, :]
else:
cov_amp = 1
n_dims = self.lower.shape[0]
initial_ls = np.ones([n_dims])
exp_kernel = george.kernels.Matern52Kernel(initial_ls,
ndim=n_dims)
kernel = cov_amp * exp_kernel
prior = DefaultPrior(len(kernel) + 1)
model = GaussianProcessMCMC(kernel, prior=prior,
n_hypers=self.n_hypers,
chain_length=self.chain_length,
burnin_steps=self.burnin,
normalize_input=False,
normalize_output=True,
rng=self.rng,
lower=self.lower,
upper=self.upper)
a = LogEI(model)
acquisition_func = MarginalizationGPMCMC(a)
max_func = Direct(acquisition_func, self.lower, self.upper, verbose=False)
model.train(self.X, self.y)
acquisition_func.update(model)
new_x = max_func.maximize()
next_config = Configuration(self.config_space, vector=new_x)
# Transform to sacred configuration
result = configspace_config_to_sacred(next_config)
return result
def bo(self, fun, seed, model_net, indes, randdes):
"""
Bayesian Optimization for ABLR
Parameters:
fun: Function_dataset object
mapping of the data
model: Net Object
seed : int
indes : Initial_design Object
"""
# BO for the network
lower = np.zeros((self.x.shape[2]))
upper = np.ones((self.x.shape[2]))
rng = np.random.RandomState(seed)
cov_amp = 2
n_dims = self.x.shape[2]
initial_ls = np.ones([n_dims])
exp_kernel = george.kernels.Matern52Kernel(initial_ls, ndim=n_dims)
kernel = cov_amp * exp_kernel
prior = DefaultPrior(len(kernel) + 1)
n_hypers = 3 * len(kernel)
if n_hypers % 2 == 1:
n_hypers += 1
model = model_net
acq = EI(model)
f = fun
#max_func = RandomSampling(acq,lower,upper,indes,n_samples=300,rng=rng)
max_func = RandomSampling(acq,
lower,
upper,
randdes,
n_samples=300,
rng=rng)
bo = BayesianOptimization(f.call,
lower=lower,
upper=upper,
acquisition_func=acq,
model=model,
initial_design=randdes.initial_design_random,
initial_points=3,
rng=rng,
maximize_func=max_func)
bo.run(num_iterations=50)
return bo.incumbents_values
def __init__(self,
objective_func,
X_lower,
X_upper,
maximizer="direct",
acquisition="LogEI",
par=None,
n_func_evals=4000,
n_iters=500):
self.objective_func = objective_func
self.X_lower = X_lower
self.X_upper = X_upper
assert self.X_upper.shape[0] == self.X_lower.shape[0]
self.task = Task(self.X_lower, self.X_upper, self.objective_func)
cov_amp = 2
initial_ls = np.ones([self.task.n_dims])
exp_kernel = george.kernels.Matern32Kernel(initial_ls,
ndim=self.task.n_dims)
kernel = cov_amp * exp_kernel
#kernel = GPy.kern.Matern52(input_dim=task.n_dims)
prior = DefaultPrior(len(kernel) + 1)
n_hypers = 3 * len(kernel)
if n_hypers % 2 == 1:
n_hypers += 1
#self.model = GaussianProcessMCMC(kernel, prior=prior, n_hypers=n_hypers, chain_length=500, burnin_steps=100)
self.model = GaussianProcess(kernel,
prior=prior,
dim=self.X_lower.shape[0],
noise=1e-3)
#self.model = GPyModel(kernel)
#MAP ESTMIATE
if acquisition == "EI":
if par is not None:
self.a = EI(self.model,
X_upper=self.task.X_upper,
X_lower=self.task.X_lower,
par=par)
else:
self.a = EI(self.model,
X_upper=self.task.X_upper,
X_lower=self.task.X_lower)
elif acquisition == "LogEI":
if par is not None:
self.a = LogEI(self.model,
X_upper=self.task.X_upper,
X_lower=self.task.X_lower,
par=par)
else:
self.a = LogEI(self.model,
X_upper=self.task.X_upper,
X_lower=self.task.X_lower)
elif acquisition == "PI":
self.a = PI(self.model,
X_upper=self.task.X_upper,
X_lower=self.task.X_lower)
elif acquisition == "UCB":
if par is not None:
self.a = LCB(self.model,
X_upper=self.task.X_upper,
X_lower=self.task.X_lower,
par=par)
else:
self.a = LCB(self.model,
X_upper=self.task.X_upper,
X_lower=self.task.X_lower)
elif acquisition == "UCB_GP":
if par is not None:
self.a = LCB_GP(self.model,
X_upper=self.task.X_upper,
X_lower=self.task.X_lower,
par=par)
else:
self.a = LCB_GP(self.model,
X_upper=self.task.X_upper,
X_lower=self.task.X_lower)
elif acquisition == "InformationGain":
self.a = InformationGain(self.model,
X_upper=self.task.X_upper,
X_lower=self.task.X_lower)
elif acquisition == "InformationGainMC":
self.a = InformationGainMC(
self.model,
X_upper=self.task.X_upper,
X_lower=self.task.X_lower,
)
else:
logger.error("ERROR: %s is not a"
"valid acquisition function!" % (acquisition))
return None
#self.acquisition_func = IntegratedAcquisition(self.model, self.a, self.task.X_lower, self.task.X_upper)
self.acquisition_func = self.a
if maximizer == "cmaes":
self.max_fkt = cmaes.CMAES(self.acquisition_func,
self.task.X_lower, self.task.X_upper)
elif maximizer == "direct":
self.max_fkt = direct.Direct(
self.acquisition_func,
self.task.X_lower,
self.task.X_upper,
n_func_evals=n_func_evals,
n_iters=n_iters) #default is n_func_evals=400, n_iters=200
elif maximizer == "stochastic_local_search":
self.max_fkt = stochastic_local_search.StochasticLocalSearch(
self.acquisition_func, self.task.X_lower, self.task.X_upper)
elif maximizer == "grid_search":
self.max_fkt = grid_search.GridSearch(self.acquisition_func,
self.task.X_lower,
self.task.X_upper)
else:
logger.error("ERROR: %s is not a valid function"
"to maximize the acquisition function!" %
(acquisition))
return None
self.bo = BayesianOptimization(acquisition_func=self.acquisition_func,
model=self.model,
maximize_func=self.max_fkt,
task=self.task)
def bayesian_optimization(objective_function,
lower,
upper,
num_iterations=30,
maximizer="random",
acquisition_func="log_ei",
model_type="gp_mcmc",
n_init=3,
rng=None,
output_path=None):
"""
General interface for Bayesian optimization for global black box
optimization problems.
Parameters
----------
objective_function: function
The objective function that is minimized. This function gets a numpy
array (D,) as input and returns the function value (scalar)
lower: np.ndarray (D,)
The lower bound of the search space
upper: np.ndarray (D,)
The upper bound of the search space
num_iterations: int
The number of iterations (initial design + BO)
maximizer: {"direct", "cmaes", "random", "scipy"}
The optimizer for the acquisition function. NOTE: "cmaes" only works in D > 1 dimensions
acquisition_func: {"ei", "log_ei", "lcb", "pi"}
The acquisition function
model_type: {"gp", "gp_mcmc", "rf"}
The model for the objective function.
n_init: int
Number of points for the initial design. Make sure that it
is <= num_iterations.
output_path: string
Specifies the path where the intermediate output after each iteration will be saved.
If None no output will be saved to disk.
rng: numpy.random.RandomState
Random number generator
Returns
-------
dict with all results
"""
assert upper.shape[0] == lower.shape[0], "Dimension miss match"
assert np.all(lower < upper), "Lower bound >= upper bound"
assert n_init <= num_iterations, "Number of initial design point has to be <= than the number of iterations"
if rng is None:
rng = np.random.RandomState(np.random.randint(0, 10000))
cov_amp = 2
n_dims = lower.shape[0]
initial_ls = np.ones([n_dims])
exp_kernel = george.kernels.Matern52Kernel(initial_ls, ndim=n_dims)
kernel = cov_amp * exp_kernel
prior = DefaultPrior(len(kernel) + 1)
n_hypers = 3 * len(kernel)
if n_hypers % 2 == 1:
n_hypers += 1
if model_type == "gp":
model = GaussianProcess(kernel,
prior=prior,
rng=rng,
normalize_output=False,
normalize_input=True,
lower=lower,
upper=upper)
elif model_type == "gp_mcmc":
model = GaussianProcessMCMC(kernel,
prior=prior,
n_hypers=n_hypers,
chain_length=200,
burnin_steps=100,
normalize_input=True,
normalize_output=True,
rng=rng,
lower=lower,
upper=upper)
elif model_type == "rf":
model = RandomForest(rng=rng)
else:
raise ValueError("'{}' is not a valid model".format(model_type))
if acquisition_func == "ei":
a = EI(model)
elif acquisition_func == "log_ei":
a = LogEI(model)
elif acquisition_func == "pi":
a = PI(model)
elif acquisition_func == "lcb":
a = LCB(model)
else:
raise ValueError("'{}' is not a valid acquisition function".format(
acquisition_func))
if model_type == "gp_mcmc":
acquisition_func = MarginalizationGPMCMC(a)
else:
acquisition_func = a
if maximizer == "cmaes":
max_func = CMAES(acquisition_func,
lower,
upper,
verbose=False,
rng=rng)
elif maximizer == "direct":
max_func = Direct(acquisition_func, lower, upper, verbose=True)
elif maximizer == "random":
max_func = RandomSampling(acquisition_func, lower, upper, rng=rng)
elif maximizer == "scipy":
max_func = SciPyOptimizer(acquisition_func, lower, upper, rng=rng)
else:
raise ValueError("'{}' is not a valid function to maximize the "
"acquisition function".format(maximizer))
bo = BayesianOptimization(objective_function,
lower,
upper,
acquisition_func,
model,
max_func,
initial_points=n_init,
rng=rng,
output_path=output_path)
x_best, f_min = bo.run(num_iterations)
results = dict()
results["x_opt"] = x_best
results["f_opt"] = f_min
results["incumbents"] = [inc for inc in bo.incumbents]
results["incumbent_values"] = [val for val in bo.incumbents_values]
results["runtime"] = bo.runtime
results["overhead"] = bo.time_overhead
results["X"] = [x.tolist() for x in bo.X]
results["y"] = [y for y in bo.y]
return results
def bayesian_optimization(objective_function,
lower,
upper,
num_iterations=30,
X_init=None,
Y_init=None,
maximizer="random",
acquisition_func="log_ei",
model_type="gp_mcmc",
n_init=3,
rng=None,
output_path=None,
kernel=None,
sampling_method="origin",
distance="cosine",
replacement=True,
pool=None,
best=None):
"""
General interface for Bayesian optimization for global black box
optimization problems.
Parameters
----------
objective_function: function
The objective function that is minimized. This function gets a numpy
array (D,) as input and returns the function value (scalar)
lower: np.ndarray (D,)
The lower bound of the search space
upper: np.ndarray (D,)
The upper bound of the search space
num_iterations: int
The number of iterations (initial design + BO)
X_init: np.ndarray(N,D)
Initial points to warmstart BO
Y_init: np.ndarray(N,1)
Function values of the already initial points
maximizer: {"random", "scipy", "differential_evolution"}
The optimizer for the acquisition function.
acquisition_func: {"ei", "log_ei", "lcb", "pi"}
The acquisition function
model_type: {"gp", "gp_mcmc", "rf", "bohamiann", "dngo"}
The model for the objective function.
n_init: int
Number of points for the initial design. Make sure that it
is <= num_iterations.
output_path: string
Specifies the path where the intermediate output after each iteration will be saved.
If None no output will be saved to disk.
rng: numpy.random.RandomState
Random number generator
kernel: george.kernels.ConstantKernel
{"constant", "polynomial", "linear", "dotproduct",
"exp", "expsquared", "matern32", "matern52", "rationalquadratic",
"cosine", "expsine2", "heuristic"}
Specify the kernel for Gaussian process.
sampling_method: {"origin", "approx", "exact"}
Specify the method to choose next sample to update model.
approx: choose the sample in the candidate pool that is closest (measured by distance
arg) to the one returned from maximizing acquisition function.
exact: evaluate all samples in the candidate pool on acquisition function
and choose the one with maximum output.
distance: {"cosine", "euclidean"}
The distance measurement for approximation sampling.
replacement: boolean
Whether to sample from pool with replacement.
pool: np.ndarray(N,D)
Candidate pool containing possible x
best: float
Stop training when the best point is sampled.
Returns
-------
dict with all results
"""
assert upper.shape[0] == lower.shape[0], "Dimension miss match"
assert np.all(lower < upper), "Lower bound >= upper bound"
assert n_init <= num_iterations, "Number of initial design point has to be <= than the number of iterations"
if rng is None:
rng = np.random.RandomState(np.random.randint(0, 10000))
cov_amp = 2
#n_dims = lower.shape[0]
#initial_ls = np.ones([n_dims])
# if kernel == "constant":
# exp_kernel = george.kernels.ConstantKernel(1, ndim=n_dims)
# elif kernel == "polynomial":
# exp_kernel = george.kernels.PolynomialKernel(log_sigma2=1, order=3, ndim=n_dims)
# elif kernel == "linear":
# exp_kernel = george.kernels.LinearKernel(log_gamma2=1, order=3, ndim=n_dims)
# elif kernel == "dotproduct":
# exp_kernel = george.kernels.DotProductKernel(ndim=n_dims)
# elif kernel == "exp":
# exp_kernel = george.kernels.ExpKernel(initial_ls, ndim=n_dims)
# elif kernel == "expsquared":
# exp_kernel = george.kernels.ExpSquaredKernel(initial_ls, ndim=n_dims)
# elif kernel == "matern32":
# exp_kernel = george.kernels.Matern32Kernel(initial_ls, ndim=n_dims)
# elif kernel == "matern52":
# exp_kernel = george.kernels.Matern52Kernel(initial_ls, ndim=n_dims)
# elif kernel == "rationalquadratic":
# exp_kernel = george.kernels.RationalQuadraticKernel(log_alpha=1, metric=initial_ls, ndim=n_dims)
# elif kernel == "cosine":
# exp_kernel = george.kernels.CosineKernel(4, ndim=n_dims)
# elif kernel == "expsine2":
# exp_kernel = george.kerngels.ExpSine2Kernel(1, 2, ndim=n_dims)
# elif kernel == "heuristic":
# exp_kernel = george.kernels.PythonKernel(heuristic_kernel_function, ndim=n_dims)
# else:
# raise ValueError("'{}' is not a valid kernel".format(kernel))
kernel = cov_amp * kernel
prior = DefaultPrior(len(kernel) + 1)
n_hypers = 3 * len(kernel)
if n_hypers % 2 == 1:
n_hypers += 1
if model_type == "gp":
model = GaussianProcess(kernel,
prior=prior,
rng=rng,
normalize_output=False,
normalize_input=True,
lower=lower,
upper=upper)
elif model_type == "gp_mcmc":
model = GaussianProcessMCMC(kernel,
prior=prior,
n_hypers=n_hypers,
chain_length=200,
burnin_steps=100,
normalize_input=True,
normalize_output=False,
rng=rng,
lower=lower,
upper=upper)
elif model_type == "rf":
model = RandomForest(rng=rng)
elif model_type == "bohamiann":
model = WrapperBohamiann()
elif model_type == "dngo":
model = DNGO()
else:
raise ValueError("'{}' is not a valid model".format(model_type))
if acquisition_func == "ei":
a = EI(model)
elif acquisition_func == "log_ei":
a = LogEI(model)
elif acquisition_func == "pi":
a = PI(model)
elif acquisition_func == "lcb":
a = LCB(model)
else:
raise ValueError("'{}' is not a valid acquisition function".format(
acquisition_func))
if model_type == "gp_mcmc":
acquisition_func = MarginalizationGPMCMC(a)
else:
acquisition_func = a
if maximizer == "random":
max_func = RandomSampling(acquisition_func, lower, upper, rng=rng)
elif maximizer == "scipy":
max_func = SciPyOptimizer(acquisition_func, lower, upper, rng=rng)
elif maximizer == "differential_evolution":
max_func = DifferentialEvolution(acquisition_func,
lower,
upper,
rng=rng)
else:
raise ValueError("'{}' is not a valid function to maximize the "
"acquisition function".format(maximizer))
if sampling_method == "exact":
max_func = ExactSampling(acquisition_func,
lower,
upper,
pool,
replacement,
rng=rng)
init_design = init_exact_random
elif sampling_method == "approx":
max_func = ApproxSampling(acquisition_func,
lower,
upper,
pool,
replacement,
distance,
rng=rng)
init_design = init_exact_random
else:
init_design = init_latin_hypercube_sampling
bo = BayesianOptimization(objective_function,
lower,
upper,
acquisition_func,
model,
max_func,
pool,
best,
sampling_method,
distance,
replacement,
initial_points=n_init,
rng=rng,
initial_design=init_design,
output_path=output_path)
x_best, f_min = bo.run(num_iterations, X=X_init, y=Y_init)
results = dict()
results["x_opt"] = x_best
results["f_opt"] = f_min
results["incumbents"] = [inc for inc in bo.incumbents]
results["incumbent_values"] = [val for val in bo.incumbents_values]
results["runtime"] = bo.runtime
results["overhead"] = bo.time_overhead
results["X"] = [x.tolist() for x in bo.X]
results["y"] = [y for y in bo.y]
return results
def entropy_search(objective_function,
lower,
upper,
num_iterations=30,
maximizer="random",
model="gp_mcmc",
n_init=3,
output_path=None,
rng=None):
"""
Entropy search for global black box optimization problems. This is a reimplemenation of the entropy search
algorithm by Henning and Schuler[1].
[1] Entropy search for information-efficient global optimization.
P. Hennig and C. Schuler.
JMLR, (1), 2012.
Parameters
----------
objective_function: function
The objective function that is minimized. This function gets a numpy array (D,) as input and returns
the function value (scalar)
lower: np.ndarray (D,)
The lower bound of the search space
upper: np.ndarray (D,)
The upper bound of the search space
num_iterations: int
The number of iterations (initial design + BO)
maximizer: {"random", "scipy", "differential_evolution"}
Defines how the acquisition function is maximized.
model: {"gp", "gp_mcmc"}
The model for the objective function.
n_init: int
Number of points for the initial design. Make sure that it is <= num_iterations.
output_path: string
Specifies the path where the intermediate output after each iteration will be saved.
If None no output will be saved to disk.
rng: numpy.random.RandomState
Random number generator
Returns
-------
dict with all results
"""
assert upper.shape[0] == lower.shape[0], "Dimension miss match"
assert np.all(lower < upper), "Lower bound >= upper bound"
assert n_init <= num_iterations, "Number of initial design point has to be <= than the number of iterations"
if rng is None:
rng = np.random.RandomState(np.random.randint(0, 10000))
cov_amp = 2
n_dims = lower.shape[0]
initial_ls = np.ones([n_dims])
exp_kernel = george.kernels.Matern52Kernel(initial_ls, ndim=n_dims)
kernel = cov_amp * exp_kernel
prior = DefaultPrior(len(kernel) + 1)
n_hypers = 3 * len(kernel)
if n_hypers % 2 == 1:
n_hypers += 1
if model == "gp":
gp = GaussianProcess(kernel,
prior=prior,
rng=rng,
normalize_output=False,
normalize_input=True,
lower=lower,
upper=upper)
elif model == "gp_mcmc":
gp = GaussianProcessMCMC(kernel,
prior=prior,
n_hypers=n_hypers,
chain_length=200,
burnin_steps=100,
normalize_input=True,
normalize_output=False,
rng=rng,
lower=lower,
upper=upper)
else:
print("ERROR: %s is not a valid model!" % model)
return
a = InformationGain(gp, lower=lower, upper=upper, sampling_acquisition=EI)
if model == "gp":
acquisition_func = a
elif model == "gp_mcmc":
acquisition_func = MarginalizationGPMCMC(a)
if maximizer == "random":
max_func = RandomSampling(acquisition_func, lower, upper, rng=rng)
elif maximizer == "scipy":
max_func = SciPyOptimizer(acquisition_func, lower, upper, rng=rng)
elif maximizer == "differential_evolution":
max_func = DifferentialEvolution(acquisition_func,
lower,
upper,
rng=rng)
else:
print(
"ERROR: %s is not a valid function to maximize the acquisition function!"
% maximizer)
return
bo = BayesianOptimization(objective_function,
lower,
upper,
acquisition_func,
gp,
max_func,
initial_design=init_latin_hypercube_sampling,
initial_points=n_init,
rng=rng,
output_path=output_path)
x_best, f_min = bo.run(num_iterations)
results = dict()
results["x_opt"] = x_best
results["f_opt"] = f_min
results["incumbents"] = [inc for inc in bo.incumbents]
results["incumbent_values"] = [val for val in bo.incumbents_values]
results["runtime"] = bo.runtime
results["overhead"] = bo.time_overhead
results["X"] = [x.tolist() for x in bo.X]
results["y"] = [y for y in bo.y]
return results
def fmin(objective_func,
X_lower,
X_upper,
num_iterations=30,
maximizer="direct",
acquisition="LogEI",
initX=None,
initY=None):
assert X_upper.shape[0] == X_lower.shape[0]
class Task(BaseTask):
def __init__(self, X_lower, X_upper, objective_fkt):
super(Task, self).__init__(X_lower, X_upper)
self.objective_function = objective_fkt
task = Task(X_lower, X_upper, objective_func)
cov_amp = 2
initial_ls = np.ones([task.n_dims])
exp_kernel = george.kernels.Matern52Kernel(initial_ls, ndim=task.n_dims)
kernel = cov_amp * exp_kernel
prior = DefaultPrior(len(kernel) + 1)
n_hypers = 3 * len(kernel)
if n_hypers % 2 == 1:
n_hypers += 1
model = GaussianProcessMCMC(kernel,
prior=prior,
n_hypers=n_hypers,
chain_length=200,
burnin_steps=100)
if acquisition == "EI":
a = EI(model, X_upper=task.X_upper, X_lower=task.X_lower)
elif acquisition == "LogEI":
a = LogEI(model, X_upper=task.X_upper, X_lower=task.X_lower)
elif acquisition == "PI":
a = PI(model, X_upper=task.X_upper, X_lower=task.X_lower)
elif acquisition == "UCB":
a = LCB(model, X_upper=task.X_upper, X_lower=task.X_lower)
elif acquisition == "InformationGain":
a = InformationGain(model, X_upper=task.X_upper, X_lower=task.X_lower)
elif acquisition == "InformationGainMC":
a = InformationGainMC(
model,
X_upper=task.X_upper,
X_lower=task.X_lower,
)
else:
logger.error("ERROR: %s is not a"
"valid acquisition function!" % (acquisition))
return None
acquisition_func = IntegratedAcquisition(model, a, task.X_lower,
task.X_upper)
if maximizer == "cmaes":
max_fkt = cmaes.CMAES(acquisition_func, task.X_lower, task.X_upper)
elif maximizer == "direct":
max_fkt = direct.Direct(acquisition_func, task.X_lower, task.X_upper)
elif maximizer == "stochastic_local_search":
max_fkt = stochastic_local_search.StochasticLocalSearch(
acquisition_func, task.X_lower, task.X_upper)
elif maximizer == "grid_search":
max_fkt = grid_search.GridSearch(acquisition_func, task.X_lower,
task.X_upper)
else:
logger.error("ERROR: %s is not a valid function"
"to maximize the acquisition function!" % (acquisition))
return None
bo = BayesianOptimization(acquisition_func=acquisition_func,
model=model,
maximize_func=max_fkt,
task=task)
best_x, f_min = bo.run(num_iterations, X=initX, Y=initY)
return task.retransform(best_x), f_min, model, acquisition_func, max_fkt
def fmin(objective_fkt,
X_lower,
X_upper,
num_iterations=30,
maximizer="direct",
acquisition_fkt="EI"):
assert X_upper.shape[0] == X_lower.shape[0]
class Task(BaseTask):
def __init__(self, X_lower, X_upper, objective_fkt):
super(Task, self).__init__(X_lower, X_upper)
self.objective_function = objective_fkt
task = Task(X_lower, X_upper, objective_fkt)
noise = 1.0
cov_amp = 2
initial_ls = np.ones([task.n_dims])
exp_kernel = george.kernels.Matern52Kernel(initial_ls, ndim=task.n_dims)
noise_kernel = george.kernels.WhiteKernel(noise, ndim=task.n_dims)
kernel = cov_amp * (exp_kernel + noise_kernel)
prior = DefaultPrior(len(kernel))
model = GaussianProcessMCMC(kernel,
prior=prior,
n_hypers=20,
chain_length=100,
burnin_steps=50)
if acquisition_fkt == "EI":
a = EI(model, X_upper=task.X_upper, X_lower=task.X_lower)
elif acquisition_fkt == "PI":
a = PI(model, X_upper=task.X_upper, X_lower=task.X_lower)
elif acquisition_fkt == "UCB":
a = LCB(model, X_upper=task.X_upper, X_lower=task.X_lower)
elif acquisition_fkt == "Entropy":
a = Entropy(model, X_upper=task.X_upper, X_lower=task.X_lower)
elif acquisition_fkt == "EntropyMC":
a = EntropyMC(
model,
X_upper=task.X_upper,
X_lower=task.X_lower,
)
else:
logger.error("ERROR: %s is not a"
"valid acquisition function!" % (acquisition_fkt))
return None
if maximizer == "cmaes":
max_fkt = cmaes.CMAES(a, task.X_lower, task.X_upper)
elif maximizer == "direct":
max_fkt = direct.Direct(a, task.X_lower, task.X_upper)
elif maximizer == "stochastic_local_search":
max_fkt = stochastic_local_search.StochasticLocalSearch(
a, task.X_lower, task.X_upper)
elif maximizer == "grid_search":
max_fkt = grid_search.GridSearch(a, task.X_lower, task.X_upper)
else:
logger.error("ERROR: %s is not a valid function"
"to maximize the acquisition function!" %
(acquisition_fkt))
return None
bo = BayesianOptimization(acquisition_func=a,
model=model,
maximize_func=max_fkt,
task=task)
best_x, f_min = bo.run(num_iterations)
return best_x, f_min
import numpy as np
from robo.models.gaussian_process_mcmc import GaussianProcessMCMC
from robo.acquisition.ei import EI
from robo.maximizers.direct import Direct
from robo.task.controlling_tasks.walker import Walker
from robo.solver.bayesian_optimization import BayesianOptimization
from robo.priors.default_priors import DefaultPrior
from robo.acquisition.integrated_acquisition import IntegratedAcquisition
task = Walker()
test = '/test'
kernel = 1 * george.kernels.Matern52Kernel(np.ones([task.n_dims]),
ndim=task.n_dims)
prior = DefaultPrior(len(kernel) + 1)
model = GaussianProcessMCMC(kernel,
prior=prior,
chain_length=100,
burnin_steps=200,
n_hypers=8)
ei = EI(model, task.X_lower, task.X_upper)
acquisition_func = IntegratedAcquisition(model, ei, task.X_lower, task.X_upper)
maximizer = Direct(acquisition_func, task.X_lower, task.X_upper)
bo = BayesianOptimization(acquisition_func=acquisition_func,
model=model,
maximize_func=maximizer,
task=task,
def bayesian_optimization(objective_function,
lower,
upper,
num_iterations=30,
maximizer="direct",
acquisition_func="log_ei",
model="gp_mcmc",
n_init=3,
rng=None):
"""
General interface for Bayesian optimization for global black box optimization problems.
Parameters
----------
objective_function: function
The objective function that is minimized. This function gets a numpy array (D,) as input and returns
the function value (scalar)
lower: np.ndarray (D,)
The lower bound of the search space
upper: np.ndarray (D,)
The upper bound of the search space
num_iterations: int
The number of iterations (initial design + BO)
maximizer: {"direct", "cmaes"}
Defines how the acquisition function is maximized. NOTE: "cmaes" only works in D > 1 dimensions
acquisition_func: {"ei", "log_ei", "lcb", "pi"}
The acquisition function
model: {"gp", "gp_mcmc"}
The model for the objective function.
n_init: int
Number of points for the initial design. Make sure that it is <= num_iterations.
rng: numpy.random.RandomState
Random number generator
Returns
-------
dict with all results
"""
assert upper.shape[0] == lower.shape[0]
assert n_init <= num_iterations, "Number of initial design point has to be <= than the number of iterations"
if rng is None:
rng = np.random.RandomState(np.random.randint(0, 10000))
cov_amp = 2
n_dims = lower.shape[0]
initial_ls = np.ones([n_dims])
exp_kernel = george.kernels.Matern52Kernel(initial_ls, ndim=n_dims)
kernel = cov_amp * exp_kernel
prior = DefaultPrior(len(kernel) + 1)
n_hypers = 3 * len(kernel)
if n_hypers % 2 == 1:
n_hypers += 1
if model == "gp":
gp = GaussianProcess(kernel,
prior=prior,
rng=rng,
normalize_output=True,
normalize_input=True,
lower=lower,
upper=upper)
elif model == "gp_mcmc":
gp = GaussianProcessMCMC(kernel,
prior=prior,
n_hypers=n_hypers,
chain_length=200,
burnin_steps=100,
normalize_input=True,
normalize_output=True,
rng=rng,
lower=lower,
upper=upper)
else:
print("ERROR: %s is not a valid model!" % model)
return
if acquisition_func == "ei":
a = EI(gp)
elif acquisition_func == "log_ei":
a = LogEI(gp)
elif acquisition_func == "pi":
a = PI(gp)
elif acquisition_func == "lcb":
a = LCB(gp)
else:
print("ERROR: %s is not a valid acquisition function!" %
acquisition_func)
return
if model == "gp":
acquisition_func = a
elif model == "gp_mcmc":
acquisition_func = MarginalizationGPMCMC(a)
if maximizer == "cmaes":
max_func = CMAES(acquisition_func,
lower,
upper,
verbose=False,
rng=rng)
elif maximizer == "direct":
max_func = Direct(acquisition_func, lower, upper, verbose=False)
else:
print(
"ERROR: %s is not a valid function to maximize the acquisition function!"
% maximizer)
return
bo = BayesianOptimization(objective_function,
lower,
upper,
acquisition_func,
gp,
max_func,
initial_points=n_init,
rng=rng)
x_best, f_min = bo.run(num_iterations)
results = dict()
results["x_opt"] = x_best
results["f_opt"] = f_min
results["incumbents"] = [inc for inc in bo.incumbents]
results["incumbent_values"] = [val for val in bo.incumbents_values]
results["runtime"] = bo.runtime
results["overhead"] = bo.time_overhead
return results
def build_prior(kernel):
"""Build default GP prior based on kernel"""
return DefaultPrior(len(kernel) + 1, numpy.random.RandomState(None))
def build_model(lower,
upper,
model_type="gp_mcmc",
model_seed=1,
prior_seed=1):
"""
General interface for Bayesian optimization for global black box
optimization problems.
Parameters
----------
lower: numpy.ndarray (D,)
The lower bound of the search space
upper: numpy.ndarray (D,)
The upper bound of the search space
model_type: {"gp", "gp_mcmc", "rf", "bohamiann", "dngo"}
The model for the objective function.
model_seed: int
Seed for random number generator of the model
prior_seed: int
Seed for random number generator of the prior
Returns
-------
Model
"""
assert upper.shape[0] == lower.shape[0], "Dimension miss match"
assert numpy.all(lower < upper), "Lower bound >= upper bound"
cov_amp = 2
n_dims = lower.shape[0]
initial_ls = numpy.ones([n_dims])
exp_kernel = george.kernels.Matern52Kernel(initial_ls, ndim=n_dims)
kernel = cov_amp * exp_kernel
prior = DefaultPrior(len(kernel) + 1, numpy.random.RandomState(prior_seed))
n_hypers = 3 * len(kernel)
if n_hypers % 2 == 1:
n_hypers += 1
# NOTE: Some models do not support RNG properly and rely on global RNG state
# so we need to seed here as well...
numpy.random.seed(model_seed)
model_rng = numpy.random.RandomState(model_seed)
if model_type == "gp":
model = GaussianProcess(kernel,
prior=prior,
rng=model_rng,
normalize_output=False,
normalize_input=True,
lower=lower,
upper=upper)
elif model_type == "gp_mcmc":
model = GaussianProcessMCMC(kernel,
prior=prior,
n_hypers=n_hypers,
chain_length=200,
burnin_steps=100,
normalize_input=True,
normalize_output=False,
rng=model_rng,
lower=lower,
upper=upper)
elif model_type == "rf":
model = RandomForest(rng=model_rng)
elif model_type == "bohamiann":
model = WrapperBohamiann()
elif model_type == "dngo":
from pybnn.dngo import DNGO
model = DNGO()
else:
raise ValueError("'{}' is not a valid model".format(model_type))
return model