def Run(self, W, x, eps, seed):
domain_dimension = len(self.domain_shape)
eps_share = util.old_div(float(eps), domain_dimension)
x = x.flatten()
prng = np.random.RandomState(seed)
Ms = []
ys = []
scale_factors = []
for i in range(domain_dimension):
# Reducde domain to get marginals
marginal_mapping = mapper.MarginalPartition(
domain_shape=self.domain_shape, proj_dim=i).mapping()
reducer = transformation.ReduceByPartition(marginal_mapping)
x_i = reducer.transform(x)
if self.domain_shape[i] < 50:
# run identity subplan
M_i = selection.Identity(x_i.shape).select()
y_i = measurement.Laplace(M_i, eps_share).measure(x_i, prng)
noise_scale_factor = laplace_scale_factor(
M_i, eps_share)
else:
# run dawa subplan
W = get_matrix(W)
W_i = W * support.expansion_matrix(marginal_mapping)
dawa = pmapper.Dawa(eps_share, 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()
y_i = measurement.Laplace(
M_bar, eps_share * (1 - self.ratio)).measure(x_bar, prng)
noise_scale_factor = laplace_scale_factor(
M_bar, eps_share * (1 - self.ratio))
# expand the dawa reduction
M_i = M_bar * support.reduction_matrix(mapping)
MM = M_i * support.reduction_matrix(marginal_mapping)
Ms.append(MM)
ys.append(y_i)
scale_factors.append(noise_scale_factor)
x_hat = inference.LeastSquares(method='lsmr').infer(Ms, ys, scale_factors)
return x_hat
def Run(self, W, x, eps, seed):
x = x.flatten()
prng = np.random.RandomState(seed)
striped_mapping = mapper.Striped(self.domain,
self.stripe_dim).mapping()
x_sub_list = meta.SplitByPartition(striped_mapping).transform(x)
Ms = []
ys = []
scale_factors = []
group_idx = sorted(set(striped_mapping))
for i in group_idx:
x_i = x_sub_list[group_idx.index(i)]
P_i = support.projection_matrix(striped_mapping, i)
M_bar = selection.HB(x_i.shape).select()
y_i = measurement.Laplace(M_bar, eps).measure(x_i, prng)
noise_scale_factor = laplace_scale_factor(M_bar, eps)
M_i = M_bar * 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 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 Run(self, W, x, eps, seed):
x = x.flatten()
prng = np.random.RandomState(seed)
domain_size = np.prod(self.domain_shape)
# Start with a unifrom estimation of x
x_hat = np.array([self.data_scale / float(domain_size)] * domain_size)
# non-zero regs to avoid super long convergence time.
nnls = inference.NonNegativeLeastSquares(l1_reg=1e-6, l2_reg=1e-6)
measuredQueries = []
M_history = []
y_history = []
noise_scales = []
if self.total_noise_scale != 0:
M_history.append(workload.Total(domain_size))
y_history.append(np.array([self.data_scale]))
noise_scales.append(self.total_noise_scale)
for i in range(1, self.rounds+1):
eps_round = eps / float(self.rounds)
# SW + SH2
worst_approx = pselection.WorstApprox(W,
measuredQueries,
x_hat,
eps_round * self.ratio)
W_next = worst_approx.select(x, prng)
measuredQueries.append(W_next.mwem_index)
M = selection.AddEquiWidthIntervals(W_next, i).select()
laplace = measurement.Laplace(M, eps_round * (1-self.ratio))
y = laplace.measure(x, prng)
# default use history
M_history.append(M)
y_history.append(y)
noise_scales.append(laplace_scale_factor(M, eps_round * (1-self.ratio)))
x_hat = nnls.infer(M_history, y_history, noise_scales)
return x_hat
def Run(self, W, x, eps, seed):
x = x.flatten()
prng = np.random.RandomState(seed)
domain_size = np.prod(self.domain_shape)
# Start with a unifrom estimation of x
x_hat = np.array([self.data_scale / float(domain_size)] * domain_size)
W = get_matrix(W)
if not isinstance(W, np.ndarray):
W = W.toarray()
measuredQueries = []
nnls = inference.NonNegativeLeastSquares(method='new')
M_history = np.empty((0, domain_size))
y_history = []
for i in range(1, self.rounds+1):
eps_round = eps / float(self.rounds)
# SW + SH2
worst_approx = pselection.WorstApprox(W,
measuredQueries,
x_hat,
eps_round * self.ratio)
W_next = worst_approx.select(x, prng)
measuredQueries.append(W_next.mwem_index)
M = selection.AddEquiWidthIntervals(W_next, i).select()
if not isinstance(M, np.ndarray):
M = M.toarray()
laplace = measurement.Laplace(M, eps_round * (1-self.ratio))
y = laplace.measure(x, prng)
# default use history
M_history = np.vstack([M_history, M])
y_history.extend(y)
if self.total_noise_scale != 0:
total_query = sparse.csr_matrix([1]*domain_size)
noise_scale = laplace_scale_factor(M, eps_round * (1-self.ratio))
x_hat = nnls.infer([total_query, M_history], [[self.data_scale], y_history], [self.total_noise_scale, noise_scale])
else:
x_hat = nnls.infer(M, y)
return x_hat
def Run(self, W, x, eps, seed):
x = x.flatten()
prng = np.random.RandomState(seed)
striped_mapping = mapper.Striped(self.domain, self.stripe_dim).mapping()
x_sub_list = meta.SplitByPartition(striped_mapping).transform(x)
Ms = []
ys = []
scale_factors = []
group_idx = sorted(set(striped_mapping))
W = get_matrix(W)
for i in group_idx:
x_i = x_sub_list[group_idx.index(i)]
P_i = support.projection_matrix(striped_mapping, i)
W_i = W * P_i.T
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))
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 Run(self, W, x, eps, seed):
prng = np.random.RandomState(seed)
domain_size = np.prod(self.domain_shape)
# Start with a unifrom estimation of x
x_hat = np.array([self.data_scale / float(domain_size)] * domain_size)
W = get_matrix(W)
W_partial = sparse.csr_matrix(W.shape)
nnls = inference.NonNegativeLeastSquares()
M_history = np.empty((0, domain_size))
y_history = []
for i in range(1, self.rounds+1):
eps_round = eps / float(self.rounds)
# SW + SH2
worst_approx = pselection.WorstApprox(sparse.csr_matrix(W),
W_partial,
x_hat,
eps_round * self.ratio)
W_next = worst_approx.select(x, prng)
M = selection.AddEquiWidthIntervals(W_next, i).select()
W_partial += W_next
laplace = measurement.Laplace(M, eps_round * (1-self.ratio))
y = laplace.measure(x, prng)
# default use history
M_history = sparse.vstack([M_history, M])
y_history.extend(y)
if self.total_noise_scale != 0:
total_query = sparse.csr_matrix([1]*domain_size)
noise_scale = laplace_scale_factor(M, eps_round * (1-self.ratio))
x_hat = nnls.infer([total_query, M_history], [[self.data_scale], y_history], [self.total_noise_scale, noise_scale])
else:
x_hat = nnls.infer(M, y)
return x_hat
def test_get_y(self):
y = Laplace(self.A, self.eps_share).measure(self.X, self.prng)
noise_scales = [laplace_scale_factor(self.A, self.eps_share)] * len(y)
np.testing.assert_array_equal(np.diag(y * get_A(self.A, noise_scales)),
get_y(y, noise_scales).flatten())
def test_get_A(self):
y = Laplace(self.A, self.eps_share).measure(self.X, self.prng)
noise_scales = [laplace_scale_factor(self.A, self.eps_share)] * len(y)
np.testing.assert_array_equal(np.array(noise_scales),
1 / np.diag(get_A(self.A, noise_scales)))
