def _build_conditional(self, Xnew, pred_noise, diag, X, Xu, y, sigma,
cov_total, mean_total):
sigma2 = at.square(sigma)
Kuu = cov_total(Xu)
Kuf = cov_total(Xu, X)
Luu = cholesky(stabilize(Kuu))
A = solve_lower(Luu, Kuf)
Qffd = at.sum(A * A, 0)
if self.approx == "FITC":
Kffd = cov_total(X, diag=True)
Lamd = at.clip(Kffd - Qffd, 0.0, np.inf) + sigma2
else: # VFE or DTC
Lamd = at.ones_like(Qffd) * sigma2
A_l = A / Lamd
L_B = cholesky(at.eye(Xu.shape[0]) + at.dot(A_l, at.transpose(A)))
r = y - mean_total(X)
r_l = r / Lamd
c = solve_lower(L_B, at.dot(A, r_l))
Kus = self.cov_func(Xu, Xnew)
As = solve_lower(Luu, Kus)
mu = self.mean_func(Xnew) + at.dot(at.transpose(As),
solve_upper(at.transpose(L_B), c))
C = solve_lower(L_B, As)
if diag:
Kss = self.cov_func(Xnew, diag=True)
var = Kss - at.sum(at.square(As), 0) + at.sum(at.square(C), 0)
if pred_noise:
var += sigma2
return mu, var
else:
cov = self.cov_func(Xnew) - at.dot(at.transpose(As), As) + at.dot(
at.transpose(C), C)
if pred_noise:
cov += sigma2 * at.identity_like(cov)
return mu, cov if pred_noise else stabilize(cov)
def square_dist(self, X, Xs=None):
X2 = aet.sum(aet.square(X), 1)
if Xs is None:
sqd = -2.0 * aet.dot(X, aet.transpose(X)) + (
aet.reshape(X2, (-1, 1)) + aet.reshape(X2, (1, -1)))
else:
Xs2 = aet.sum(aet.square(Xs), 1)
sqd = -2.0 * aet.dot(X, aet.transpose(Xs)) + (
aet.reshape(X2, (-1, 1)) + aet.reshape(Xs2, (1, -1)))
return aet.clip(sqd, 0.0, np.inf)
def full(self, X, Xs=None):
X, Xs = self._slice(X, Xs)
rx = self.lfunc(at.as_tensor_variable(X), self.args)
if Xs is None:
rz = self.lfunc(at.as_tensor_variable(X), self.args)
r2 = self.square_dist(X, X)
else:
rz = self.lfunc(at.as_tensor_variable(Xs), self.args)
r2 = self.square_dist(X, Xs)
rx2 = at.reshape(at.square(rx), (-1, 1))
rz2 = at.reshape(at.square(rz), (1, -1))
return at.sqrt((2.0 * at.outer(rx, rz)) / (rx2 + rz2)) * at.exp(-1.0 * r2 / (rx2 + rz2))
def square_dist(self, X, Xs):
X = at.mul(X, 1.0 / self.ls)
X2 = at.sum(at.square(X), 1)
if Xs is None:
sqd = -2.0 * at.dot(X, at.transpose(X)) + (at.reshape(X2,
(-1, 1)) +
at.reshape(X2, (1, -1)))
else:
Xs = at.mul(Xs, 1.0 / self.ls)
Xs2 = at.sum(at.square(Xs), 1)
sqd = -2.0 * at.dot(X, at.transpose(Xs)) + (
at.reshape(X2, (-1, 1)) + at.reshape(Xs2, (1, -1)))
return at.clip(sqd, 0.0, np.inf)
def _build_marginal_likelihood_logp(self, y, X, Xu, sigma):
sigma2 = at.square(sigma)
Kuu = self.cov_func(Xu)
Kuf = self.cov_func(Xu, X)
Luu = cholesky(stabilize(Kuu))
A = solve_lower(Luu, Kuf)
Qffd = at.sum(A * A, 0)
if self.approx == "FITC":
Kffd = self.cov_func(X, diag=True)
Lamd = at.clip(Kffd - Qffd, 0.0, np.inf) + sigma2
trace = 0.0
elif self.approx == "VFE":
Lamd = at.ones_like(Qffd) * sigma2
trace = (1.0 /
(2.0 * sigma2)) * (at.sum(self.cov_func(X, diag=True)) -
at.sum(at.sum(A * A, 0)))
else: # DTC
Lamd = at.ones_like(Qffd) * sigma2
trace = 0.0
A_l = A / Lamd
L_B = cholesky(at.eye(Xu.shape[0]) + at.dot(A_l, at.transpose(A)))
r = y - self.mean_func(X)
r_l = r / Lamd
c = solve_lower(L_B, at.dot(A, r_l))
constant = 0.5 * X.shape[0] * at.log(2.0 * np.pi)
logdet = 0.5 * at.sum(at.log(Lamd)) + at.sum(at.log(at.diag(L_B)))
quadratic = 0.5 * (at.dot(r, r_l) - at.dot(c, c))
return -1.0 * (constant + logdet + quadratic + trace)
def full(self, X, Xs=None):
X, Xs = self._slice(X, Xs)
if Xs is None:
Xs = X
f1 = X.dimshuffle(0, "x", 1)
f2 = Xs.dimshuffle("x", 0, 1)
r = np.pi * (f1 - f2) / self.period
r = at.sum(at.square(at.sin(r) / self.ls), 2)
return at.exp(-0.5 * r)
def _build_conditional(self, Xnew, pred_noise, diag, X, y, noise, cov_total, mean_total):
Kxx = cov_total(X)
Kxs = self.cov_func(X, Xnew)
Knx = noise(X)
rxx = y - mean_total(X)
L = cholesky(stabilize(Kxx) + Knx)
A = solve_lower(L, Kxs)
v = solve_lower(L, rxx)
mu = self.mean_func(Xnew) + at.dot(at.transpose(A), v)
if diag:
Kss = self.cov_func(Xnew, diag=True)
var = Kss - at.sum(at.square(A), 0)
if pred_noise:
var += noise(Xnew, diag=True)
return mu, var
else:
Kss = self.cov_func(Xnew)
cov = Kss - at.dot(at.transpose(A), A)
if pred_noise:
cov += noise(Xnew)
return mu, cov if pred_noise else stabilize(cov)
def _build_conditional(self, Xnew, pred_noise, diag):
Xs, y, sigma = self.Xs, self.y, self.sigma
# Old points
X = cartesian(*Xs)
delta = y - self.mean_func(X)
Kns = [f(x) for f, x in zip(self.cov_funcs, Xs)]
eigs_sep, Qs = zip(*map(eigh, Kns)) # Unzip
QTs = list(map(at.transpose, Qs))
eigs = kron_diag(*eigs_sep) # Combine separate eigs
if sigma is not None:
eigs += sigma**2
# New points
Km = self.cov_func(Xnew, diag=diag)
Knm = self.cov_func(X, Xnew)
Kmn = Knm.T
# Build conditional mu
alpha = kron_dot(QTs, delta)
alpha = alpha / eigs[:, None]
alpha = kron_dot(Qs, alpha)
mu = at.dot(Kmn, alpha).ravel() + self.mean_func(Xnew)
# Build conditional cov
A = kron_dot(QTs, Knm)
A = A / at.sqrt(eigs[:, None])
if diag:
Asq = at.sum(at.square(A), 0)
cov = Km - Asq
if pred_noise:
cov += sigma
else:
Asq = at.dot(A.T, A)
cov = Km - Asq
if pred_noise:
cov += sigma * at.identity_like(cov)
return mu, cov
def log_diff_normal_cdf(mu, sigma, x, y):
"""
Compute :math:`\\log(\\Phi(\frac{x - \\mu}{\\sigma}) - \\Phi(\frac{y - \\mu}{\\sigma}))` safely in log space.
Parameters
----------
mu: float
mean
sigma: float
std
x: float
y: float
must be strictly less than x.
Returns
-------
log (\\Phi(x) - \\Phi(y))
"""
x = (x - mu) / sigma / aet.sqrt(2.0)
y = (y - mu) / sigma / aet.sqrt(2.0)
# To stabilize the computation, consider these three regions:
# 1) x > y > 0 => Use erf(x) = 1 - e^{-x^2} erfcx(x) and erf(y) =1 - e^{-y^2} erfcx(y)
# 2) 0 > x > y => Use erf(x) = e^{-x^2} erfcx(-x) and erf(y) = e^{-y^2} erfcx(-y)
# 3) x > 0 > y => Naive formula log( (erf(x) - erf(y)) / 2 ) works fine.
return aet.log(0.5) + aet.switch(
aet.gt(y, 0),
-aet.square(y) + aet.log(
aet.erfcx(y) -
aet.exp(aet.square(y) - aet.square(x)) * aet.erfcx(x)),
aet.switch(
aet.lt(x, 0), # 0 > x > y
-aet.square(x) + aet.log(
aet.erfcx(-x) -
aet.exp(aet.square(x) - aet.square(y)) * aet.erfcx(-y)),
aet.log(aet.erf(x) - aet.erf(y)), # x >0 > y
),
)
def diag(self, X):
X, _ = self._slice(X, None)
cov_diag = self.cov_func(X, diag=True)
scf_diag = at.square(at.flatten(self.scaling_func(X, self.args)))
return cov_diag * scf_diag
def diag(self, X):
X, Xc, _ = self._common(X, None)
return at.sum(at.square(Xc), 1)
def full(self, X, Xs=None):
X, Xs = self._slice(X, Xs)
r = self.euclidean_dist(X, Xs)
return (1.0 + np.sqrt(5.0) * r + 5.0 / 3.0 * at.square(r)) * at.exp(
-1.0 * np.sqrt(5.0) * r)
def diag(self, X):
return at.alloc(at.square(self.sigma), X.shape[0])
def volatility_update(x, vol, w, a, b):
return at.sqrt(w + a * at.square(x) + b * at.square(vol))
