def gen_data_to_s3(bucket, obj_func_min, num_pts, which_IS, key):
search_domain = pythonTensorProductDomain([
ClosedInterval(bound[0], bound[1])
for bound in obj_func_min._search_domain
])
points = search_domain.generate_uniform_random_points_in_domain(num_pts)
vals = [obj_func_min.evaluate(which_IS, pt) for pt in points]
noise = obj_func_min.noise_and_cost_func(which_IS, None) * np.ones(num_pts)
data = {"points": points, "vals": vals, "noise": noise}
send_data_to_s3(bucket, key, data)
def gen_data_to_pickle(directory, obj_func_min, num_pts, which_IS, filename):
search_domain = pythonTensorProductDomain([
ClosedInterval(bound[0], bound[1])
for bound in obj_func_min._search_domain
])
points = search_domain.generate_uniform_random_points_in_domain(num_pts)
vals = [obj_func_min.evaluate(which_IS, pt) for pt in points]
noise = obj_func_min.noise_and_cost_func(which_IS, None) * np.ones(num_pts)
data = {"points": points, "vals": vals, "noise": noise}
with open(filename, "wb") as file:
pickle.dump(data, file)
def coldstart_gen_data(obj_func_min, num_init_pts, num_replications, directory):
""" generate initial data for experiments and store in pickle
"""
for replication_no in range(num_replications):
filename = "{0}/{1}_{2}_points_each_repl_{3}.pickle".format(directory, obj_func_min.getFuncName(), num_init_pts, replication_no)
search_domain = pythonTensorProductDomain([ClosedInterval(bound[0], bound[1]) for bound in obj_func_min._search_domain]) # this file is used below again and hence should be made available there, too
points = search_domain.generate_uniform_random_points_in_domain(num_init_pts)
vals = [obj_func_min.evaluate(0, pt) for pt in points]
data = {"points": points, "vals": vals, "noise": obj_func_min.noise_and_cost_func(0, None)[0] * numpy.ones(num_init_pts)}
with open(filename, "wb") as file:
pickle.dump(data, file)
def find_best_mu_ei(gp, domain_bounds, num_multistart):
search_domain = pythonTensorProductDomain(
[ClosedInterval(bound[0], bound[1]) for bound in domain_bounds])
start_points = search_domain.generate_uniform_random_points_in_domain(
num_multistart)
min_mu = numpy.inf
for start_point in start_points:
x, f = bfgs_optimization(start_point, compute_mu(gp), domain_bounds)
if min_mu > f:
min_mu = f
point = x
return min_mu, point
def optimize_hyperparameters(problem_search_domain,
points_sampled,
points_sampled_value,
points_sampled_noise_variance,
upper_bound_noise_variances=10.,
consider_small_variances=True,
hyper_prior=None,
num_restarts=32,
num_jobs=16):
'''
Fit hyperparameters from data using MLE or MAP (described in Poloczek, Wang, and Frazier 2016)
:param problem_search_domain: The search domain of the benchmark, as provided by the benchmark
:param points_sampled: An array that gives the points sampled so far. Each points has the form [IS dim0 dim1 ... dimn]
:param points_sampled_value: An array that gives the values observed at the points in same ordering
:param upper_bound_noise_variances: An upper bound on the search interval for the noise variance parameters (before squaring)
:param consider_small_variances: If true, half of the BFGS starting points have entries for the noise parameters set to a small value
:param hyper_prior: use prior for MAP estimate if supplied, and do MLE otherwise
:param num_restarts: number of starting points for BFGS to find MLE/MAP
:param num_jobs: number of parallelized BFGS instances
:return: An array with the best found values for the hyperparameters
'''
approx_grad = True
upper_bound_signal_variances = numpy.maximum(
10., numpy.var(points_sampled_value)) # pick huge upper bounds
hyper_bounds = generate_hyperbounds(problem_search_domain,
upper_bound_noise_variances,
upper_bound_signal_variances)
hyperparam_search_domain = pythonTensorProductDomain(
[ClosedInterval(bd[0], bd[1]) for bd in hyper_bounds])
hyper_multistart_pts = hyperparam_search_domain.generate_uniform_random_points_in_domain(
num_restarts)
for i in xrange(num_restarts):
init_hyper = hyper_multistart_pts[i]
# if optimization is enabled, make sure that small variances are checked despite multi-modality
# this optimization seems softer than using a MAP estimate
if consider_small_variances and (i % 2 == 0):
init_hyper[
-1] = 0.1 # use a small value as starting point for noise parameters in BFGS
hyper_multistart_pts[i] = init_hyper
parallel_results = Parallel(n_jobs=num_jobs)(
delayed(hyper_opt)(points_sampled, points_sampled_value,
points_sampled_noise_variance, init_hyper,
hyper_bounds, approx_grad, hyper_prior)
for init_hyper in hyper_multistart_pts)
# print min(parallel_results,key=itemgetter(1))
best_hyper = min(
parallel_results, key=itemgetter(1)
)[0] # recall that we negated the log marginal likelihood when passing it to BFGS
return best_hyper
def check_ave_min(func_idx):
num_repl = 500
func = func_list[func_idx]
search_domain = pythonTensorProductDomain(
[ClosedInterval(bound[0], bound[1]) for bound in func._search_domain])
min_vals = np.zeros((num_repl, len(num_pts_list)))
for i, num_pts in enumerate(num_pts_list):
for repl in range(num_repl):
points = search_domain.generate_uniform_random_points_in_domain(
num_pts)
min_vals[repl,
i] = np.amin([func.evaluate(0, pt) for pt in points])
return np.mean(min_vals, axis=0).tolist()
def coldstart_gen_hyperdata(primary_obj_func_min, list_other_obj_func_min, num_pts, directory):
""" generate data for hyperparameter optimization and store in pickle
"""
filename = "{0}/hyper_{1}_points_{2}_{3}.pickle".format(directory, num_pts, primary_obj_func_min.getFuncName(), "_".join([func.getFuncName() for func in list_other_obj_func_min]))
search_domain = pythonTensorProductDomain([ClosedInterval(bound[0], bound[1]) for bound in primary_obj_func_min._search_domain]) # this file is used below again and hence should be made available there, too
points = search_domain.generate_uniform_random_points_in_domain(num_pts)
vals = [[primary_obj_func_min.evaluate(0, pt) for pt in points]]
noise = [primary_obj_func_min.noise_and_cost_func(0, None)]
for obj_func in list_other_obj_func_min:
vals.append([obj_func.evaluate(0, pt) for pt in points])
noise.append(obj_func.noise_and_cost_func(0, None))
data = {"points": points, "vals": vals, "noise": noise}
with open(filename, "wb") as file:
pickle.dump(data, file)
def test_normal_prior(self):
space_dim = 2
num_IS = 2
true_hyper, data = get_random_gp_data(space_dim, num_IS, 500)
hyperparam_search_domain = pythonTensorProductDomain([ClosedInterval(bound[0], bound[1]) for bound in numpy.repeat([[0.01, 2.]], len(true_hyper), axis=0)])
hyper_bounds = [(0.01, 100.) for i in range(len(true_hyper))]
multistart_pts = hyperparam_search_domain.generate_uniform_random_points_in_domain(1)
cov = MixedSquareExponential(hyperparameters=multistart_pts[0,:], total_dim=space_dim+1, num_is=num_IS)
test_prior = NormalPrior(5.*numpy.ones(len(true_hyper)), 25. * numpy.eye(len(true_hyper)))
hyper_test, f, output = hyper_opt(cov, data=data, init_hyper=multistart_pts[0, :], hyper_bounds=hyper_bounds, approx_grad=False, hyper_prior=test_prior)
good_prior = NormalPrior(true_hyper, 0.1 * numpy.eye(len(true_hyper)))
hyper_good_prior, _, _ = hyper_opt(cov, data=data, init_hyper=multistart_pts[0, :], hyper_bounds=hyper_bounds, approx_grad=False, hyper_prior=good_prior)
bad_prior = NormalPrior(numpy.ones(len(true_hyper)), 0.1 * numpy.eye(len(true_hyper)))
hyper_bad_prior, _, _ = hyper_opt(cov, data=data, init_hyper=multistart_pts[0, :], hyper_bounds=hyper_bounds, approx_grad=False, hyper_prior=bad_prior)
print "true hyper: {0}\n hyper test: {1}\n good prior: {2}\n bad prior:\n should close to one {3}".format(true_hyper, hyper_test, hyper_good_prior, hyper_bad_prior)
print "dim {0}, num_is {1}".format(space_dim, num_IS)
def global_optimization_of_GP(gp_model,
bounds,
num_multistart,
minimization=True):
"""
:param gp_model:
:param bounds: list of (min, max) tuples
:param num_multistart:
:param minimization:
:return: shape(space_dim+1,), best x and first entry is always zero because we assume IS0 is truth IS
"""
sgn = 1 if minimization else -1
fcn = lambda x: gp_model.compute_mean_of_points(
np.concatenate([[0], x]).reshape((1, -1)))[0] * sgn
grad = lambda x: gp_model.compute_grad_mean_of_points(
np.concatenate([[0], x]).reshape(
(1, -1)), num_derivatives=1)[0, 1:] * sgn
search_domain = pythonTensorProductDomain(
[ClosedInterval(bound[0], bound[1]) for bound in bounds])
start_points = search_domain.generate_uniform_random_points_in_domain(
num_multistart)
min_fcn = np.inf
for start_pt in start_points:
result_x, result_f, output = scipy.optimize.fmin_l_bfgs_b(
func=fcn,
x0=start_pt,
fprime=grad,
args=(),
approx_grad=False,
bounds=bounds,
m=10,
factr=10.0,
pgtol=1e-10,
epsilon=1e-08,
iprint=-1,
maxfun=15000,
maxiter=200,
disp=0,
callback=None)
if result_f < min_fcn:
min_fcn = result_f
ret = result_x
print "found GP min {0}".format(min_fcn)
return np.concatenate([[0], ret]).reshape((1, -1))
def optimize_with_ego(gp, domain_bounds, num_multistart):
expected_improvement_evaluator = ExpectedImprovement(gp)
search_domain = pythonTensorProductDomain(
[ClosedInterval(bound[0], bound[1]) for bound in domain_bounds])
start_points = search_domain.generate_uniform_random_points_in_domain(
num_multistart)
min_negative_ei = numpy.inf
def negative_ego_func(x):
expected_improvement_evaluator.set_current_point(x.reshape((1, -1)))
return -1.0 * expected_improvement_evaluator.compute_expected_improvement(
)
for start_point in start_points:
x, f = bfgs_optimization(start_point, negative_ego_func, domain_bounds)
if min_negative_ei > f:
min_negative_ei = f
point_to_sample = x
return point_to_sample, -min_negative_ei
def optimize_entropy(pes,
pes_model,
space_dim,
num_discretization,
cost_func,
list_sample_is,
bounds=None):
if not bounds:
bounds = [(0., 1.)] * space_dim
# fcn = lambda x: np.mean([pes.acquisition({'obj': pes_model}, {}, np.concatenate([[which_is], x]), current_best=None, compute_grad=False)[0,0] for pes_model in pes_model_list]) * -1. / cost
# search_domain = pythonTensorProductDomain([ClosedInterval(bound[0], bound[1]) for bound in bounds])
# start_points = search_domain.generate_uniform_random_points_in_domain(num_multistart)
# min_fcn = np.inf
# for start_pt in start_points:
# result_x, result_f, output = scipy.optimize.fmin_l_bfgs_b(func=fcn, x0=start_pt, fprime=None, args=(), approx_grad=True,
# bounds=bounds, m=10, factr=10.0, pgtol=1e-10,
# epsilon=1e-08, iprint=-1, maxfun=15000, maxiter=200, disp=0, callback=None)
# if result_f < min_fcn:
# min_fcn = result_f
# ret = result_x
# return np.concatenate([[which_is], ret]), -min_fcn
search_domain = pythonTensorProductDomain(
[ClosedInterval(bound[0], bound[1]) for bound in bounds])
points = search_domain.generate_uniform_random_points_in_domain(
num_discretization)
raw_acq = [] # for tuning costs
best_acq = -np.inf
for which_is in list_sample_is:
acq_list = pes.acquisition(
{'obj': pes_model}, {},
np.hstack((np.ones((num_discretization, 1)) * which_is, points)),
current_best=None,
compute_grad=False) / cost_func(which_is, None)
inner_best_idx = np.argmax(acq_list)
raw_acq.append(acq_list[inner_best_idx] * cost_func(which_is, None))
if acq_list[inner_best_idx] > best_acq:
best_acq = acq_list[inner_best_idx]
best_is = which_is
best_idx = inner_best_idx
return points[best_idx, :], best_is, best_acq, raw_acq
def optimize_with_multifidelity_ei(gp_list, domain_bounds, num_IS,
num_multistart, noise_and_cost_func):
multifidelity_expected_improvement_evaluator = MultifidelityExpectedImprovement(
gp_list, noise_and_cost_func)
search_domain = pythonTensorProductDomain(
[ClosedInterval(bound[0], bound[1]) for bound in domain_bounds])
start_points = search_domain.generate_uniform_random_points_in_domain(
num_multistart)
min_negative_ei = numpy.inf
def negative_ei_func(x):
return -1.0 * multifidelity_expected_improvement_evaluator.compute_expected_improvement(
x)
for start_point in start_points:
x, f = bfgs_optimization(start_point, negative_ei_func, domain_bounds)
if min_negative_ei > f:
min_negative_ei = f
point_to_sample = x
return point_to_sample, multifidelity_expected_improvement_evaluator.choose_IS(
point_to_sample), -min_negative_ei
def get_random_gp_data(space_dim, num_is, num_data_each_is, kernel_name):
""" Generate random gp data
:param space_dim:
:param num_is:
:param num_data_each_is:
:param kernel_name: currently it's either 'mix_exp' or 'prod_ker'
:return:
"""
sample_var = 0.01
if kernel_name == "mix_exp":
hyper_params = numpy.random.uniform(size=(num_is + 1) *
(space_dim + 1))
cov = MixedSquareExponential(hyper_params, space_dim + 1, num_is)
elif kernel_name == "prod_ker":
hyper_params = numpy.random.uniform(size=(num_is + 1) *
(num_is + 2) / 2 + space_dim + 1)
cov = ProductKernel(hyper_params, space_dim + 1, num_is + 1)
else:
raise NotImplementedError("invalid kernel")
python_search_domain = pythonTensorProductDomain([
ClosedInterval(bound[0], bound[1])
for bound in numpy.repeat([[-10., 10.]], space_dim + 1, axis=0)
])
data = HistoricalData(space_dim + 1)
init_pts = python_search_domain.generate_uniform_random_points_in_domain(2)
init_pts[:, 0] = numpy.zeros(2)
data.append_historical_data(init_pts, numpy.zeros(2),
numpy.ones(2) * sample_var)
gp = GaussianProcess(cov, data)
points = python_search_domain.generate_uniform_random_points_in_domain(
num_data_each_is)
for pt in points:
for i in range(num_is):
pt[0] = i
val = gp.sample_point_from_gp(pt, sample_var)
data.append_sample_points([
[pt, val, sample_var],
])
gp = GaussianProcess(cov, data)
return hyper_params, data
def generate_data(self, num_data):
python_search_domain = pythonTensorProductDomain([
ClosedInterval(bound[0], bound[1])
for bound in self._info_dict['search_domain']
])
data = HistoricalData(self._info_dict['dim'])
init_pts = python_search_domain.generate_uniform_random_points_in_domain(
2)
init_pts[:, 0] = numpy.zeros(2)
data.append_historical_data(init_pts, numpy.zeros(2),
numpy.ones(2) * self._sample_var_1)
gp = GaussianProcess(self._cov, data)
points = python_search_domain.generate_uniform_random_points_in_domain(
num_data)
for pt in points:
pt[0] = numpy.ceil(numpy.random.uniform(high=2.0, size=1))
sample_var = self._sample_var_1 if pt[
0] == 1 else self._sample_var_2
val = gp.sample_point_from_gp(pt, sample_var)
data.append_sample_points([
[pt, val, sample_var],
])
gp = GaussianProcess(self._cov, data)
return data
"StybTang": StybTang(
act_var, low_dim, high_to_low, sign, bx_size, noise_var=noise_var
),
"MNIST": MNIST(act_var, low_dim, high_to_low, sign, bx_size),
}
objective_func = obj_func_dict[obj_func_name]
dim = int(objective_func._dim)
num_initial_points = initial_n
num_fidelity = objective_func._num_fidelity
inner_search_domain = pythonTensorProductDomain(
[
ClosedInterval(
objective_func._search_domain[i, 0], objective_func._search_domain[i, 1]
)
for i in range(objective_func._search_domain.shape[0] - num_fidelity)
]
)
cpp_search_domain = cppTensorProductDomain(
[ClosedInterval(bound[0], bound[1]) for bound in objective_func._search_domain]
)
cpp_inner_search_domain = cppTensorProductDomain(
[
ClosedInterval(
objective_func._search_domain[i, 0], objective_func._search_domain[i, 1]
)
for i in range(objective_func._search_domain.shape[0] - num_fidelity)
]
)
obj_func_max = Rosenbrock(numIS, mult=-1.0) # used by KG
obj_func_min = Rosenbrock(
numIS,
mult=1.0) # our original problems are all assumed to be minimization!
# less important params
exploitation_threshold = 1e-5
num_x_prime = 3000
num_discretization_before_ranking = num_x_prime * 3
num_iterations = 100
num_threads = 64
num_multistart = 64
num_candidate_start_points = 500
### end parameter
search_domain = pythonTensorProductDomain([
ClosedInterval(bound[0], bound[1]) for bound in obj_func_max._search_domain
])
noise_and_cost_func = obj_func_min.noise_and_cost_func
# Load initial data from pickle
init_pts = load_init_points_for_all_IS("pickles", init_data_pickle_filename,
obj_func_min._numIS)
init_vals = load_vals("pickles", init_data_pickle_filename,
obj_func_min._numIS)
#init_pts, init_vals = sample_initial_points.load_data_from_a_min_problem("pickles", init_data_pickle_filename)
# setup benchmark result container
multi_kg_result = BenchmarkResult(num_iterations, obj_func_max._dim,
benchmark_result_table_name)
kg_hyper_param = pandas.read_sql_table(
'multifidelity_kg_hyperparam_' + func_name,
data_list, bias_sq_list = createHistoricalDataForMisoEI(obj_func_min.getDim(), listPrevData, directory=pathToPickles, bias_filename=bias_filename)
###############################################
###############################################
### Begin hyper opt
hyper_result = []
for data in data_list:
# Setup prior for MAP
prior_mean = np.concatenate(([np.var(data.points_sampled_value)], [1.]*obj_func_min.getDim()))
prior_sig = np.eye(obj_func_min.getDim()+1) * 100.
prior_sig[0,0] = np.power(prior_mean[0]/5., 2.)
prior = NormalPrior(prior_mean, prior_sig)
hyper_bounds = [(0.1, prior_mean[i]+2.*np.sqrt(prior_sig[i,i])) for i in range(obj_func_min.getDim()+1)]
print "hyper bound {0}".format(hyper_bounds)
hyperparam_search_domain = pythonTensorProductDomain([ClosedInterval(bound[0], bound[1]) for bound in hyper_bounds])
multistart_pts = hyperparam_search_domain.generate_uniform_random_points_in_domain(num_hyper_multistart)
best_f = np.inf
cov = SquareExponential(prior_mean)
for i in range(num_hyper_multistart):
hyper, f, output = hyper_opt(cov, data=data, init_hyper=multistart_pts[i, :],
hyper_bounds=hyper_bounds, approx_grad=False, hyper_prior=prior)
# print output
if f < best_f:
best_hyper = hyper
best_f = f
print 'best_hyper=' + str(best_hyper)
print 'best_f= ' + str(best_f)
print "prior mean is: {0}".format(prior_mean)
hyper_result = np.concatenate((hyper_result, best_hyper))
sql_util.write_array_to_table("mei_hyper_{0}".format(obj_func_min.getFuncName()), hyper_result)
def miso_gen_data():
"""
This script intend to do the same thing as sample_initial_points.py, with the only difference that it calls AssembleToOrderPES
as objective, which place truth_is at IS0. This is required by Entropy Search algo and also makes sense when truth IS is accessible.
"""
### Need to set the following parameters!
#obj_func_min = RosenbrockShifted( )
obj_func_min = AssembleToOrderPES(mult=-1.0)
# obj_func_min = RosenbrockNoiseFreePES(mult=1.0)
# obj_func_min = RosenbrockNewNoiseFreePES(mult=1.0)
# list of IS that are to be queried
list_IS_to_query = obj_func_min.getList_IS_to_query() #[1,2,3] # [0]# for coldstart # range(obj_func_min._num_IS)
#string_list_IS_to_query = 'IS_' + '_'.join(str(element) for element in list_IS_to_query)
# print string_list_IS_to_query
# exit(0)
# create initial data for runs
num_init_pts_each_IS = 20 ###5 # for Rosenbrock # 20 # for ATO
num_replications = 100
# # create data for hyper opt.
# num_init_pts_each_IS = 200
# num_replications = 3
allows_parallelization = True # set to True if each simulator/IS can be queried multiple times simultaneously
# is True for rosenbrock and ATO
# is False for dragAndLift
### end
directory = "/fs/europa/g_pf/pickles/miso"
for replication_no in range(num_replications):
filename = obj_func_min.getFuncName() + '_' + 'IS_' + '_'.join(str(element) for element in list_IS_to_query) \
+ '_' + str(num_init_pts_each_IS) + "_points_each"
if num_replications > 1:
filename += '_repl_' + str(replication_no)
print 'filename=' + filename
search_domain = pythonTensorProductDomain([ClosedInterval(bound[0], bound[1]) for bound in obj_func_min._search_domain]) # this file is used below again and hence should be made available there, too
init_points_for_all_IS = []
init_vals_all_IS = []
is_list = []
def parallel_func(IS, pt):
return obj_func_min.evaluate(IS, pt)
num_parallel_jobs = num_init_pts_each_IS # Jialei's original choice
if(('ato' in obj_func_min.getFuncName()) and (num_parallel_jobs > 10)): # do not start too many MATLAB instances
num_parallel_jobs = 10
if(not allows_parallelization):
num_parallel_jobs = 1
index_Array = 0 # which entry of the array to write into?
with Parallel(n_jobs=num_parallel_jobs) as parallel:
for index_IS in list_IS_to_query:
print "{0}th IS".format(index_IS)
points = search_domain.generate_uniform_random_points_in_domain(num_init_pts_each_IS)
init_points_for_all_IS.append(points)
vals = parallel(delayed(parallel_func)(index_IS, pt) for pt in init_points_for_all_IS[index_Array])
init_vals_all_IS.append(vals)
is_list.append(numpy.ones(num_init_pts_each_IS)*index_IS)
index_Array +=1
print "min value: {0}".format(numpy.amin(init_vals_all_IS))
data = {"points": init_points_for_all_IS, "vals": init_vals_all_IS, "IS": is_list}
with open("{0}/{1}.pickle".format(directory, filename), "wb") as file:
pickle.dump(data, file)
based on Jialei's Rosenbrock code -- Many Thanks!
'''
# the next lines are dependent on the problem
func_name = 'assembleToOrder'
obj_func_max = AssembleToOrder(numIS=4)
num_pts_to_gen = 100 # numpy.repeat( 250, obj_func_max.getNumIS())
hyper_bounds = [
(0.01, 100)
for i in range((obj_func_max.getDim() + 1) * (obj_func_max.getNumIS() + 1))
]
num_hyper_multistart = 5
search_domain = pythonTensorProductDomain([
ClosedInterval(bound[0], bound[1])
for bound in obj_func_max.getSearchDomain()
])
### Gen points for hyperparam estimation
data = HistoricalData(obj_func_max.getDim() +
1) # should go into the objective func obj
for i in range(obj_func_max.getNumIS()):
pts = search_domain.generate_uniform_random_points_in_domain(
num_pts_to_gen)
vals = [obj_func_max.evaluate(i + 1, pt) for pt in pts]
IS_pts = numpy.hstack(((i + 1) * numpy.ones(num_pts_to_gen).reshape(
(-1, 1)), pts))
sample_vars = [
obj_func_max.noise_and_cost_func(i + 1, pt)[0] for pt in pts
]
data.append_historical_data(IS_pts, vals, sample_vars)
def obtainHistoricalDataForEGO(load_historical_data_from_pickle,
obj_func_min,
directoryToPickles,
list_IS_to_query,
num_init_pts_each_IS,
init_data_pickle_filename=''):
'''
Create Historical Data object for EGO that contains initial data.
If truthIS is among the IS, then load only the data from that one
Args:
load_historical_data_from_pickle: if True load from pickle otherwise do a random Latin hypercube design
obj_func_min: the problem
directoryToPickles: path to the directory that contains the pickle files
list_IS_to_query: list of the IS that should be queried, e.g. [0, 1, 2]
num_init_pts_each_IS: how many points for each IS - is either used to find right pickle or to determine the number of points to sample
init_data_pickle_filename: optional parameter that gives the filename of the pickle to load
Returns: HistoricalData object
'''
historical_data = HistoricalData(obj_func_min._dim)
if (load_historical_data_from_pickle):
# To load the pickled data, do:
if (init_data_pickle_filename == ''):
init_data_pickle_filename = obj_func_min.getFuncName() + '_' + 'IS_' \
+ '_'.join(str(element) for element in list_IS_to_query) + '_' \
+ str(num_init_pts_each_IS) + "_points_each"
init_pts_array, init_vals_array = load_data_from_a_min_problem(
directoryToPickles, init_data_pickle_filename)
# if truthIS is among the sampled, then load only that one:
if obj_func_min.getTruthIS() in list_IS_to_query:
indexArray = list_IS_to_query.index(obj_func_min.getTruthIS())
sample_vars = [
obj_func_min.noise_and_cost_func(obj_func_min.getTruthIS(),
pt)[0]
for pt in init_pts_array[indexArray]
]
historical_data.append_historical_data(init_pts_array[indexArray],
init_vals_array[indexArray],
sample_vars)
else:
# load data for all IS
indexArray = 0
for index_IS in list_IS_to_query:
sample_vars = [
obj_func_min.noise_and_cost_func(index_IS, pt)[0]
for pt in init_pts_array[indexArray]
]
historical_data.append_historical_data(
init_pts_array[indexArray], init_vals_array[indexArray],
sample_vars)
indexArray += 1
else:
# generate initial data from querying random points for each IS
for index_IS in list_IS_to_query:
if (obj_func_min.getTruthIS() in list_IS_to_query) and (
index_IS != obj_func_min.getTruthIS()):
continue # the truthIS is observed but this is another IS: skip!
search_domain = pythonTensorProductDomain([
ClosedInterval(bound[0], bound[1])
for bound in obj_func_min._search_domain
])
pts = search_domain.generate_uniform_random_points_in_domain(
num_init_pts_each_IS)
vals = [obj_func_min.evaluate(index_IS, pt) for pt in pts]
sample_vars = [
obj_func_min.noise_and_cost_func(index_IS, pt)[0] for pt in pts
]
historical_data.append_historical_data(pts, vals, sample_vars)
return historical_data
pickle_vals(directory, func_name, obj_func_min.getNumIS(), vals)
if __name__ == "__main__":
### Need to set the following parameters!
obj_func_min = DragAndLift(mult=1.0)
directory = "pickles"
#num_init_pts_each_IS = 10
allows_parallelization = False # set to True if each simulator/IS can be queried multiple times simultaneously
# is True for rosenbrock and ATO
# is False for dragAndLift
### end
# specific to each scenario
search_domain = pythonTensorProductDomain([
ClosedInterval(bound[0], bound[1])
for bound in obj_func_min.getSearchDomain()
])
# this file is used below again and hence should be made available there, too
lastExistingSetId = 1 # prevent existing datasets from being overwritten
for num_init_pts_each_IS in [10, 10]: # [5, 10, 10, 5, 5]:
init_points_for_all_IS = []
# IS 1 and 2 at the same points
points = search_domain.generate_uniform_random_points_in_domain(
num_init_pts_each_IS)
init_points_for_all_IS.append(points)
init_points_for_all_IS.append(points)
# IS 3 and 4 at the same points
points = search_domain.generate_uniform_random_points_in_domain(
allows_parallelization = True # set to True if each simulator/IS can be queried multiple times simultaneously
# is True for rosenbrock and ATO
# is False for dragAndLift
### end
directory = "../pickles/csCentered"
for replication_no in range(num_replications):
filename = obj_func_min.getFuncName() + '_' + 'IS_' + '_'.join(str(element) for element in list_IS_to_query) \
+ '_' + str(num_init_pts_each_IS) + "_points_each"
if num_replications > 1:
filename += '_repl_' + str(replication_no)
print 'filename=' + filename
search_domain = pythonTensorProductDomain(
[
ClosedInterval(bound[0], bound[1])
for bound in obj_func_min._search_domain
]
) # this file is used below again and hence should be made available there, too
init_points_for_all_IS = []
init_vals_all_IS = []
def parallel_func(IS, pt):
return obj_func_min.evaluate(IS, pt)
num_parallel_jobs = num_init_pts_each_IS # Jialei's original choice
if (('ato' in obj_func_min.getFuncName())
and (num_parallel_jobs >
10)): # do not start too many MATLAB instances
num_parallel_jobs = 10
if (not allows_parallelization):
num_parallel_jobs = 1
hist_data_grad.append_historical_data(gp_grad_info_dict['points'],
gp_grad_info_dict['values'],
gp_grad_info_dict['vars'])
print gp_grad_info_dict['values']
objective_func = synthetic_functions.RandomGP(
gp_grad_info_dict['dim'], gp_grad_info_dict['hyper_params'],
hist_data_grad)
hyper_params = gp_grad_info_dict['hyper_params']
init_pts = [[-2.0], [0.0], [0.3], [0.5]]
ymax = 1
else:
objective_func = obj_func_dict[obj_func_name]
#init_data = utils.get_init_data_from_db(objective_func._dim, objective_func._sample_var, utils.sql_engine, 'init_points_'+obj_func_name)
python_search_domain = pythonTensorProductDomain([
ClosedInterval(bound[0], bound[1])
for bound in objective_func._search_domain
])
cpp_search_domain = cppTensorProductDomain([
ClosedInterval(bound[0], bound[1])
for bound in objective_func._search_domain
])
result = numpy.zeros((num_iteration, 6))
best_so_far_kg = numpy.zeros((end_idx - start_idx, num_iteration + 1))
# begin job
for job_no in xrange(start_idx, end_idx):
python_search_domain = pythonTensorProductDomain([
ClosedInterval(bound[0], bound[1])
for bound in objective_func._search_domain
])
def optimize_hyperparameters(num_IS,
problem_search_domain,
points_sampled,
points_sampled_value,
upper_bound_noise_variances=10.,
consider_small_variances=True,
hyper_prior=None,
num_restarts=32,
num_jobs=16):
'''
Fit hyperparameters from data using MLE or MAP (described in Poloczek, Wang, and Frazier 2016)
:param num_IS: The total number of information sources
:param problem_search_domain: The search domain of the benchmark, as provided by the benchmark
:param points_sampled: An array that gives the points sampled so far. Each points has the form [IS dim0 dim1 ... dimn]
:param points_sampled_value: An array that gives the values observed at the points in same ordering
:param upper_bound_noise_variances: An upper bound on the search interval for the noise variance parameters (before squaring)
:param consider_small_variances: If true, half of the BFGS starting points have entries for the noise parameters set to a small value
:param hyper_prior: use prior for MAP estimate if supplied, and do MLE otherwise
:param num_restarts: number of starting points for BFGS to find MLE/MAP
:param num_jobs: number of parallelized BFGS instances
:return: An array with the best found values for the hyperparameters
'''
approx_grad = True
upper_bound_signal_variances = numpy.maximum(
10., numpy.var(points_sampled_value)) # pick huge upper bounds
hyper_bounds = generate_hyperbounds(num_IS, problem_search_domain,
upper_bound_noise_variances,
upper_bound_signal_variances)
hyperparam_search_domain = pythonTensorProductDomain(
[ClosedInterval(bd[0], bd[1]) for bd in hyper_bounds])
hyper_multistart_pts = hyperparam_search_domain.generate_uniform_random_points_in_domain(
num_restarts)
dim = len(
problem_search_domain
) + 1 # 1 + the dimension of the search space that the points are from
# best_f = numpy.inf
for i in xrange(num_restarts):
init_hyper = hyper_multistart_pts[i]
# if optimization is enabled, make sure that small variances are checked despite multi-modality
# this optimization seems softer than using a MAP estimate
if consider_small_variances and (i % 2 == 0):
for j in xrange(num_IS):
init_hyper[
-1 -
j] = 0.1 # use a small value as starting point for noise parameters in BFGS
# # print init_hyper
# # print hyper_bounds
# # print len(init_hyper)
# # print len(hyper_bounds)
# # print hyper_multistart_pts.shape
# # exit(0)
# # If hypers are optimized sequentially
# hyper, f, output = hyper_opt(num_IS, dim, points_sampled, points_sampled_value, init_hyper, hyper_bounds, approx_grad)
# # print output
# if f < best_f: # recall that we negated the log marginal likelihood when passing it to BFGS
# best_hyper = hyper
# best_f = f
# # print "itr {0}, hyper: {1}, negative log marginal likelihood: {2}".format(i, hyper, f)
#
# only if opt. hypers in parallel:
hyper_multistart_pts[i] = init_hyper
parallel_results = Parallel(n_jobs=num_jobs)(
delayed(hyper_opt)(num_IS, dim, points_sampled, points_sampled_value,
init_hyper, hyper_bounds, approx_grad, hyper_prior)
for init_hyper in hyper_multistart_pts)
# print min(parallel_results,key=itemgetter(1))
best_hyper = min(
parallel_results, key=itemgetter(1)
)[0] # recall that we negated the log marginal likelihood when passing it to BFGS
# print 'best_hyper = ' + str(best_hyper) + ' with -log(prob[Y|D]) = ' \
# + str(min(parallel_results,key=itemgetter(1))[1]) \
# + ' for upper_bound_noise_variances = ' + str(upper_bound_noise_variances)
# # hyperparameters_without_noise = best_hyper[:(num_IS * dim)]
# # noise_hyperparameters = best_hyper[(num_IS * dim):]
# # print compute_covariance_matrix(dim, hyperparameters_without_noise, noise_hyperparameters, points_sampled)
# # test using hypers from big dataset
# def obj_func(x):
# '''
# The negative marginal loglikelihood for hyperparameters x
# Args:
# x: the hyperparameters, including noise hyperparameters appended to the hyperparameters of the kernels
#
# Returns: The negated value of the marginal loglikelihood at hyperparameters x
# '''
#
# # split x into hyperparameters and noise_hyperparameters
# # For each IS there are dim signal variances and length scales
# hyperparameters_without_noise = x[:(num_IS * dim)]
# noise_hyperparameters = x[(num_IS * dim):]
# # print 'hyperparameters_without_noise = ' + str(hyperparameters_without_noise)
# # print 'noise_hyperparameters = ' + str(noise_hyperparameters)
#
# # # compute the parts of the marginal loglikelihood
# covariance_matrix = compute_covariance_matrix(dim, hyperparameters_without_noise, noise_hyperparameters, points_sampled)
#
# K_chol = scipy.linalg.cho_factor(covariance_matrix, lower=True, overwrite_a=True)
# K_inv_y = scipy.linalg.cho_solve(K_chol, points_sampled_value)
#
# # This BFGS minimizes but we wish to maximize, thus negate the log marginal likelihood
# return -1.0 * compute_log_likelihood(K_chol, K_inv_y, points_sampled_value)
# # hypers for RbRemi on large dataset with known noise
# init_hyper = numpy.array([6.99174646e+05, 7.26756985e-01, 3.04331525, 1.20070203,
# 1.65571854e-01, 3.28218161e-01, 1e-1, 1e-1])
# # # hypers for RbNew on large dataset with known noise
# # init_hyper = numpy.array([ 6.89212443e+05, 7.06559876e-01, 2.98432914e+00, 2.05984746e+00,
# # 1.16904675e-01, 2.23726117e-01, 1.0, 1e-1])
# print 'hypers from large dataset with known noise have -log p(Y|D) of ' + str(obj_func(init_hyper))
# hyper, f, output = hyper_opt(num_IS, dim, points_sampled, points_sampled_value, init_hyper, hyper_bounds, approx_grad)
# print 'starting from opt hyper = ' + str(hyper) + ", f=" + str(f) #+ ", output = " + str(output)
# exit(0)
return best_hyper
