def update(self, Z, num_new=1, log_weights=None):
assert (len(Z) >= num_new)
# dont do anything if no data observed
if num_new == 0:
return
if log_weights is not None:
assert len(log_weights) == len(Z)
else:
log_weights = np.zeros(len(Z))
Z_new = Z[-num_new:]
log_weights_new = log_weights[-num_new:]
# first update: use first of X and log_weights, and then discard
if self.log_sum_weights is None:
# assume have observed fake terms, which is needed for making the system well-posed
# the L_C says that the fake terms had covariance self.lmbda, which is a regulariser
self.L_C = np.eye(self.D) * np.sqrt(self.gamma2)
self.log_sum_weights = log_weights_new[0]
self.mu = Z_new[0]
Z_new = Z_new[1:]
log_weights_new = log_weights_new[1:]
num_new -= 1
# dont do anything if no data observed
if len(Z_new) == 0:
return
# generate lmbdas that correspond to weighted averages
lmbdas = log_weights_to_lmbdas(self.log_sum_weights, log_weights_new)
# low-rank update of Cholesky, costs O(d^2) only
old_L_C = np.array(self.L_C, copy=True)
self.mu, self.L_C = update_mean_cov_L_lmbda(Z_new, self.mu, self.L_C,
lmbdas)
if np.any(np.isnan(self.L_C)) or np.any(np.isinf(self.L_C)):
logger.warning(
"Numerical error while updating Cholesky factor of C.\n"
"Before update:\n%s\n"
"After update:\n%s\n"
"Updating data:\n%s\n"
"Updating log weights:\n%s\n"
"Updating lmbdas:\n%s\n" % (str(old_L_C), str(
self.L_C), str(Z_new), str(log_weights_new), str(lmbdas)))
raise RuntimeError(
"Numerical error while updating Cholesky factor of C.")
# update terms and weights
self.log_sum_weights = logsumexp(
list(log_weights) + [self.log_sum_weights])
def test_weights_to_lmbdas_equals_log_version():
N = 30
sum_old_weights = 1
new_weights = np.ones(N - 1)
lmbdas = weights_to_lmbdas(sum_old_weights, new_weights)
log_sum_old_weights = np.log(sum_old_weights)
log_new_weights = np.log(new_weights)
lmbdas2 = log_weights_to_lmbdas(log_sum_old_weights, log_new_weights)
assert_allclose(lmbdas, lmbdas2)
def test_weights_to_lmbdas_equals_log_version():
N = 30
sum_old_weights = 1
new_weights = np.ones(N - 1)
lmbdas = weights_to_lmbdas(sum_old_weights, new_weights)
log_sum_old_weights = np.log(sum_old_weights)
log_new_weights = np.log(new_weights)
lmbdas2 = log_weights_to_lmbdas(log_sum_old_weights, log_new_weights)
assert_allclose(lmbdas, lmbdas2)
def update(self, Z, num_new=1, log_weights=None):
assert(len(Z) >= num_new)
# dont do anything if no data observed
if num_new == 0:
return
if log_weights is not None:
assert len(log_weights) == len(Z)
else:
log_weights = np.zeros(len(Z))
Z_new = Z[-num_new:]
log_weights_new = log_weights[-num_new:]
# first update: use first of X and log_weights, and then discard
if self.log_sum_weights is None:
# assume have observed fake terms, which is needed for making the system well-posed
# the L_C says that the fake terms had covariance self.lmbda, which is a regulariser
self.L_C = np.eye(self.D) * np.sqrt(self.gamma2)
self.log_sum_weights = log_weights_new[0]
self.mu = Z_new[0]
Z_new = Z_new[1:]
log_weights_new = log_weights_new[1:]
num_new -= 1
# dont do anything if no data observed
if len(Z_new) == 0:
return
# generate lmbdas that correspond to weighted averages
lmbdas = log_weights_to_lmbdas(self.log_sum_weights, log_weights_new)
# low-rank update of Cholesky, costs O(d^2) only
old_L_C = np.array(self.L_C, copy=True)
self.mu, self.L_C = update_mean_cov_L_lmbda(Z_new, self.mu, self.L_C, lmbdas)
if np.any(np.isnan(self.L_C)) or np.any(np.isinf(self.L_C)):
logger.warning("Numerical error while updating Cholesky factor of C.\n"
"Before update:\n%s\n"
"After update:\n%s\n"
"Updating data:\n%s\n"
"Updating log weights:\n%s\n"
"Updating lmbdas:\n%s\n"
% (str(old_L_C), str(self.L_C), str(Z_new), str(log_weights_new), str(lmbdas))
)
raise RuntimeError("Numerical error while updating Cholesky factor of C.")
# update terms and weights
self.log_sum_weights = logsumexp(list(log_weights) + [self.log_sum_weights])
