def test_rhess_02():
n, d = (50, 3)
alpha = randint(1, 10, 2) * .1
beta = randint(1, 10, 2)[0] * .1
man = ComplexPositiveSemidefinite(n, d, alpha=alpha, beta=beta)
S = man.rand()
# simple function. Distance to a given matrix
# || S - A||_F^2
A = hsym(crandn(n, n))
def f(S):
diff = (A - S.Y @ S.P @ S.Y.T.conjugate())
return trace(diff @ diff.T.conjugate())
def df(S):
return psd_ambient(-4 * A @ S.Y @ S.P,
2 * (S.P - S.Y.T.conjugate() @ A @ S.Y))
def ehess_form(S, xi, eta):
return (
trace(-4 * A @ (xi.tY @ S.P + S.Y @ xi.tP) @ eta.tY.T.conjugate())
+ 2 * trace(
(xi.tP - xi.tY.T.conjugate() @ A @ S.Y -
S.Y.T.conjugate() @ A @ xi.tY) @ eta.tP.T.conjugate())).real
def ehess_vec(S, xi):
return psd_ambient(
-4 * A @ (xi.tY @ S.P + S.Y @ xi.tP),
2 * (xi.tP - xi.tY.T.conjugate() @ A @ S.Y -
S.Y.T.conjugate() @ A @ xi.tY))
xxi = man.randvec(S)
dlt = 1e-8
Snew = psd_point(S.Y + dlt * xxi.tY, S.P + dlt * xxi.tP)
d1 = (f(Snew) - f(S)) / dlt
d2 = df(S)
print(d1 - man.base_inner_ambient(d2, xxi))
eeta = man.randvec(S)
d1 = man.base_inner_ambient((df(Snew) - df(S)), eeta) / dlt
ehess_val = ehess_form(S, xxi, eeta)
dv2 = ehess_vec(S, xxi)
print(man.base_inner_ambient(dv2, eeta))
print(d1, ehess_val, d1 - ehess_val)
# now check the formula: ehess = xi (eta_func(f)) - <D_xi eta, df(Y)>
# promote eta to a vector field.
m1 = crandn(n, n)
m2 = crandn(d, d)
m_p = crandn(d * d, d * d)
def eta_field(Sin):
return man.proj(
S,
psd_ambient(m1 @ (Sin.Y - S.Y) @ m2,
hsym((m_p @ (Sin.P - S.P).reshape(-1)).reshape(
d, d)))) + eeta
# xietaf: should go to ehess(xi, eta) + df(Y) @ etafield)
xietaf = (man.base_inner_ambient(df(Snew), eta_field(Snew)) -
man.base_inner_ambient(df(S), eta_field(S))) / dlt
# appy eta_func to f: should go to tr(m1 @ xxi @ m2 @ df(Y).T)
Dxietaf = man.base_inner_ambient(
(eta_field(Snew) - eta_field(S)), df(S)) / dlt
# this is ehess. should be same as d1 or ehess_val
print(xietaf - Dxietaf)
print(xietaf - Dxietaf - ehess_val)
# now check: rhess. Need to make sure xi, eta in the tangent space.
# first compare this with numerical differentiation
xi1 = man.proj(S, xxi)
eta1 = man.proj(S, eeta)
egvec = df(S)
ehvec = ehess_vec(S, xi1)
rhessvec = man.ehess2rhess(S, egvec, ehvec, xi1)
# check it numerically:
def rgrad_func(Y):
return man.proj_g_inv(Y, df(Y))
# val2a, _, _ = calc_covar_numeric_raw(man, W, xi1, df)
val2, _, _ = calc_covar_numeric(man, S, xi1, rgrad_func)
val2_p = man.proj(S, val2)
# print(rhessvec)
# print(val2_p)
print(man._vec(rhessvec - val2_p))
rhessval = man.inner_product_amb(S, rhessvec, eta1)
print(man.inner_product_amb(S, val2, eta1))
print(rhessval)
# check symmetric:
ehvec_e = ehess_vec(S, eta1)
rhessvec_e = man.ehess2rhess(S, egvec, ehvec_e, eta1)
rhessval_e = man.inner_product_amb(S, rhessvec_e, xi1)
print(rhessval_e)
# the above computed inner_prod(Nabla_xi Pi * df, eta)
# in the following check. Extend eta1 to eta_proj
# (Pi Nabla_hat Pi g_inv df, g eta)
# = D_xi (Pi g_inv df, g eta) - (Pi g_inv df g Pi Nabla_hat eta)
def eta_proj(S):
return man.proj(S, eta_field(S))
print(check_zero(man._vec(eta1 - eta_proj(S))))
e1 = man.inner(S, man.proj_g_inv(S, df(S)), eta_proj(S))
e1a = man.base_inner_ambient(df(S), eta_proj(S))
print(e1, e1a, e1 - e1a)
Snew = psd_point(S.Y + dlt * xi1.tY, S.P + dlt * xi1.tP)
e2 = man.inner(Snew, man.proj_g_inv(Snew, df(Snew)), eta_proj(Snew))
e2a = man.base_inner_ambient(df(Snew), eta_proj(Snew))
print(e2, e2a, e2 - e2a)
first = (e2 - e1) / dlt
first1 = (man.base_inner_ambient(df(Snew), eta_proj(Snew)) -
man.base_inner_ambient(df(S), eta_proj(S))) / dlt
print(first - first1)
val3, _, _ = calc_covar_numeric(man, S, xi1, eta_proj)
second = man.inner(S, man.proj_g_inv(S, df(S)), man.proj(S, val3))
second2 = man.inner(S, man.proj_g_inv(S, df(S)), val3)
print(second, second2, second - second2)
print('same as rhess_val %f' % (first - second))
def test_covariance_deriv():
# now test full:
# do covariant derivatives
# check that it works, preseving everything
n, d = (5, 3)
alpha = randint(1, 10, 2) * .1
beta = randint(1, 10, 2)[0] * .01
man = ComplexPositiveSemidefinite(n, d, alpha=alpha, beta=beta)
S = man.rand()
aa = crandn(n * d, n * d)
cc = crandn(d * d, d * d)
icpt = man._rand_ambient()
def omg_func(S):
csp = hsym((cc @ S.P.reshape(-1)).reshape(d, d))
return psd_ambient(
(aa @ S.Y.reshape(-1) + icpt.tY.reshape(-1)).reshape(n, d),
csp + icpt.tP)
xi = man.randvec(S)
egrad = omg_func(S)
ecsp = hsym((cc @ xi.tP.reshape(-1)).reshape(d, d))
ehess = psd_ambient((aa @ xi.tY.reshape(-1)).reshape(n, d), ecsp)
val1 = man.ehess2rhess(S, egrad, ehess, xi)
def rgrad_func(W):
return man.proj_g_inv(W, omg_func(W))
if False:
first = ehess
a = man.J_g_inv(S, egrad)
rgrad = man.proj_g_inv(S, egrad)
second = man.D_g(S, xi, man.g_inv(S, egrad)).scalar_mul(-1)
aout = man.solve_J_g_inv_Jst(S, a)
third = man.proj(S, man.D_g_inv_Jst(S, xi, aout)).scalar_mul(-1)
fourth = man.christoffel_form(S, xi, rgrad)
val1a1 = man.proj_g_inv(S, first + second + fourth) + third
print(check_zero(man._vec(val1 - val1a1)))
elif True:
d_xi_rgrad = num_deriv_amb(man, S, xi, rgrad_func)
rgrad = man.proj_g_inv(S, egrad)
fourth = man.christoffel_form(S, xi, rgrad)
val1a = man.proj(S, d_xi_rgrad) + man.proj_g_inv(S, fourth)
print(check_zero(man._vec(val1 - val1a)))
# nabla_v_xi, dxi, cxxi
val2a, _, _ = calc_covar_numeric(man, S, xi, omg_func)
val2, _, _ = calc_covar_numeric(man, S, xi, rgrad_func)
# val2_p = project(prj, val2)
val2_p = man.proj(S, val2)
# print(val1)
# print(val2_p)
print(check_zero(man._vec(val1) - man._vec(val2_p)))
if True:
H = xi
valrangeA_ = ehess + man.g(S, man.D_proj(
S, H, man.g_inv(S, egrad))) - man.D_g(
S, H, man.g_inv(S, egrad)) +\
man.christoffel_form(S, H, man.proj_g_inv(S, egrad))
valrangeB = man.proj_g_inv(S, valrangeA_)
valrange = man.ehess2rhess_alt(S, egrad, ehess, xi)
print(check_zero(man._vec(valrange) - man._vec(val2_p)))
print(check_zero(man._vec(valrange) - man._vec(val1)))
print(check_zero(man._vec(valrange) - man._vec(valrangeB)))