def Run(self, W, x, eps, seed):
x = x.flatten()
prng = np.random.RandomState(seed)
striped_vectors = mapper.Striped(self.domain, self.stripe_dim).partitions()
hd_vector = support.combine_all(striped_vectors)
striped_mapping = hd_vector.flatten()
x_sub_list = meta.SplitByPartition(striped_mapping).transform(x)
Ms = []
ys = []
scale_factors = []
group_idx = sorted(set(striped_mapping))
# Given a group id on the full vector, recover the group id for each partition
# put back in loop to save memory
self.subgroups = {}
for i in group_idx:
selected_idx = np.where(hd_vector == i)
ans = [p[i[0]] for p, i in zip(striped_vectors, selected_idx)]
self.subgroups[i] = ans
for i in group_idx:
x_i = x_sub_list[group_idx.index(i)]
# overwriting standard projection for efficiency
W_i = self.project_workload(W, striped_vectors, hd_vector, i)
dawa = pmapper.Dawa(eps, self.ratio, self.approx)
mapping = dawa.mapping(x_i, prng)
reducer = transformation.ReduceByPartition(mapping)
x_bar = reducer.transform(x_i)
W_bar = W_i * support.expansion_matrix(mapping)
M_bar = selection.GreedyH(x_bar.shape, W_bar).select()
if not isinstance(M_bar, np.ndarray):
M_bar = M_bar.toarray()
y_i = measurement.Laplace(
M_bar, eps * (1 - self.ratio)).measure(x_bar, prng)
noise_scale_factor = laplace_scale_factor(
M_bar, eps * (1 - self.ratio))
# convert the measurement back to the original domain for inference
P_i = support.projection_matrix(striped_mapping, i)
M_i = (M_bar * support.reduction_matrix(mapping)) * P_i
Ms.append(M_i)
ys.append(y_i)
scale_factors.append(noise_scale_factor)
x_hat = inference.LeastSquares().infer(Ms, ys, scale_factors)
return x_hat
def mapping(self):
assert self.proj_dim < len(self.domain_shape), "proj_dim out of range"
margin_vec = [np.array([1] * i) for i in self.domain_shape]
margin_vec[self.proj_dim] = np.arange(
self.domain_shape[self.proj_dim]) # the projecting dimension
return support.combine_all(margin_vec).flatten()
def Run(self, W, x, eps):
striped_vectors = striped_partition(self.domain_shape, self.stripe_dim)
hd_vector = support.combine_all(striped_vectors)
striped_mapping = hd_vector.flatten()
x_sub_list = x.split_by_partition(striped_mapping)
Ms = []
ys = []
scale_factors = []
group_idx = sorted(set(striped_mapping))
# Given a group id on the full vector, recover the group id for each partition
# put back in loop to save memory
self.subgroups = {}
for i in group_idx:
selected_idx = np.where(hd_vector == i)
ans = [p[i[0]] for p, i in zip(striped_vectors, selected_idx)]
self.subgroups[i] = ans
for i in group_idx:
x_i = x_sub_list[group_idx.index(i)]
# overwriting standard projection for efficiency
W_i = self.project_workload(W, striped_vectors, hd_vector, i)
mapping = x_i.dawa(self.ratio, self.approx, eps)
x_bar = x_i.reduce_by_partition(mapping)
W_bar = W_i * support.expansion_matrix(mapping)
M_bar = greedyH((len(set(mapping)), ), W_bar)
y_i = x_bar.laplace(M_bar, eps * (1 - self.ratio))
noise_scale_factor = laplace_scale_factor(M_bar,
eps * (1 - self.ratio))
# convert the measurement back to the original domain for inference
P_i = support.projection_matrix(striped_mapping, i)
M_i = (M_bar * support.reduction_matrix(mapping)) * P_i
Ms.append(M_i)
ys.append(y_i)
scale_factors.append(laplace_scale_factor(M_bar, eps))
x_hat = least_squares(Ms, ys, scale_factors)
return x_hat
def mapping(self):
vectors = [np.arange(dom, dtype=int) for dom in self.domain_size]
vectors[self.stripe_dim] = np.ones(self.domain_size[self.stripe_dim],
dtype=int)
return support.combine_all(vectors).flatten()
