def embed_SDP(P,order="AMD",cholmod=False):
if not isinstance(P,SDP): raise ValueError, "not an SDP object"
if order=='AMD':
from cvxopt.amd import order
elif order=='METIS':
from cvxopt.metis import order
else: raise ValueError, "unknown ordering: %s " %(order)
p = order(P.V)
if cholmod:
from cvxopt import cholmod
V = +P.V + spmatrix([float(i+1) for i in xrange(P.n)],xrange(P.n),xrange(P.n))
F = cholmod.symbolic(V,p=p)
cholmod.numeric(V,F)
f = cholmod.getfactor(F)
fd = [(j,i) for i,j in enumerate(f[:P.n**2:P.n+1])]
fd.sort()
ip = matrix([j for _,j in fd])
Ve = chompack.tril(chompack.perm(chompack.symmetrize(f),ip))
Ie = misc.sub2ind((P.n,P.n),Ve.I,Ve.J)
else:
#Vc,n = chompack.embed(P.V,p)
symb = chompack.symbolic(P.V,p)
#Ve = chompack.sparse(Vc)
Ve = symb.sparsity_pattern(reordered=False)
Ie = misc.sub2ind((P.n,P.n),Ve.I,Ve.J)
Pe = SDP()
Pe._A = +P.A; Pe._b = +P.b
Pe._A[:,0] += spmatrix(0.0,Ie,[0 for i in range(len(Ie))],(Pe._A.size[0],1))
Pe._agg_sparsity()
Pe._pname = P._pname + "_embed"
Pe._ischordal = True; Pe._blockstruct = P._blockstruct
return Pe
def sparse_chol(M, perm=None, retF=False, retP=True, retL=True):
# Quick check that M is square
if M.size[0] != M.size[1]:
raise Exception('M must be square.')
# Set the factorisation to use LL' instead of LDL'
cholmod.options['supernodal'] = 2
if not perm is None:
# Make an expression for the factorisation
F = cholmod.symbolic(M, p=perm)
else:
# Make an expression for the factorisation
F = cholmod.symbolic(M)
# Calculate the factorisation
cholmod.numeric(M, F)
# Empty factorisation object
factorisation = {}
if retF:
# Calculate the factorisation again (buggy if returning L for
# some reason)
F2 = cholmod.symbolic(M, p=perm)
cholmod.numeric(M, F2)
# If we want to return the F object, add it to the dictionary
factorisation['F'] = F2
if retP:
# Set p to [0,...,n-1]
P = cvxopt.matrix(range(M.size[0]), (M.size[0], 1), tc='d')
# Solve and replace p with the true permutation used
cholmod.solve(F, P, sys=7)
# Convert p into an integer array; more useful that way
P = cvxopt.matrix(np.array(P).astype(np.int64), tc='i')
# If we want to return the permutation, add it to the dictionary
factorisation['P'] = P
if retL:
# Get the sparse cholesky factor
L = cholmod.getfactor(F)
# If we want to return the factor, add it to the dictionary
factorisation['L'] = L
# Return P and L
return (factorisation)
def eval(obj):
try:
s = cholmod.options['supernodal']
except KeyError:
s = 2 # set to default.
cholmod.options['supernodal'] = 0
A = cvxopt.base.sparse(obj)
F = cholmod.symbolic(A)
cholmod.numeric(A, F)
Di = matrix(1.0, (4, 1))
cholmod.solve(F, Di, sys=6)
# Reset state.
cholmod.options['supernodal'] = s
return -sum(cvxopt.base.log(Di))
def eval(obj):
try:
s = cholmod.options['supernodal']
except KeyError:
s = 2 # set to default.
cholmod.options['supernodal'] = 0
A = cvxopt.base.sparse(obj)
F = cholmod.symbolic(A)
cholmod.numeric(A, F)
Di = matrix(1.0, (4,1))
cholmod.solve(F, Di, sys=6)
# Reset state.
cholmod.options['supernodal'] = s
return -sum(cvxopt.base.log(Di))
def sp_det_sym(M):
# Change to the LL' decomposition
prevopts = cholmod.options['supernodal']
cholmod.options['supernodal'] = 2
# Obtain decomposition of M
F = cholmod.symbolic(M)
cholmod.numeric(M, F)
# Restore previous options
cholmod.options['supernodal'] = prevopts
# As PMP'=LL' and det(P)=1 for all permutations
# it follows det(M)=det(L)^2=product(diag(L))^2
return (np.exp(2 * sum(cvxopt.log(cholmod.diag(F)))))
def covsel(Y):
"""
Returns the solution of
minimize -log det K + Tr(KY)
subject to K_{ij}=0, (i,j) not in indices listed in I,J.
Y is a symmetric sparse matrix with nonzero diagonal elements.
I = Y.I, J = Y.J.
"""
I, J = Y.I, Y.J
n, m = Y.size[0], len(I)
N = I + J*n # non-zero positions for one-argument indexing
D = [k for k in range(m) if I[k]==J[k]] # position of diagonal elements
# starting point: symmetric identity with nonzero pattern I,J
K = spmatrix(0.0, I, J)
K[::n+1] = 1.0
# Kn is used in the line search
Kn = spmatrix(0.0, I, J)
# symbolic factorization of K
F = cholmod.symbolic(K)
# Kinv will be the inverse of K
Kinv = matrix(0.0, (n,n))
for iters in range(100):
# numeric factorization of K
cholmod.numeric(K, F)
d = cholmod.diag(F)
# compute Kinv by solving K*X = I
Kinv[:] = 0.0
Kinv[::n+1] = 1.0
cholmod.solve(F, Kinv)
# solve Newton system
grad = 2*(Y.V - Kinv[N])
hess = 2*(mul(Kinv[I,J],Kinv[J,I]) + mul(Kinv[I,I],Kinv[J,J]))
v = -grad
lapack.posv(hess,v)
# stopping criterion
sqntdecr = -blas.dot(grad,v)
print("Newton decrement squared:%- 7.5e" %sqntdecr)
if (sqntdecr < 1e-12):
print("number of iterations: ", iters+1)
break
# line search
dx = +v
dx[D] *= 2 # scale the diagonal elems
f = -2.0 * sum(log(d)) # f = -log det K
s = 1
for lsiter in range(50):
Kn.V = K.V + s*dx
try:
cholmod.numeric(Kn, F)
except ArithmeticError:
s *= 0.5
else:
d = cholmod.diag(F)
fn = -2.0 * sum(log(d)) + 2*s*blas.dot(v,Y.V)
if (fn < f - 0.01*s*sqntdecr):
break
s *= 0.5
K.V = Kn.V
return K
# Read in ffx variance
sigma2 = pandas.read_csv('true_ffxvar.csv', header=None).values
ZtZ = cvxopt.spmatrix.trans(Z2) * Z2
# Use minimum degree ordering
P = amd.order(ZtZ)
# Set the factorisation to use LL' instead of LDL'
cholmod.options['supernodal'] = 2
# Make an expression for the factorisation
F = cholmod.symbolic(ZtZ, p=P)
# Calculate the factorisation
cholmod.numeric(ZtZ, F)
# Get the sparse cholesky factorisation
L = cholmod.getfactor(F)
LLt = L * cvxopt.spmatrix.trans(L)
# Create initial lambda
# Work out how many lambda components needed
f1_n_lamcomps = np.int64(f1_nv * (f1_nv + 1) / 2)
f2_n_lamcomps = np.int64(f2_nv * (f2_nv + 1) / 2)
# Work out triangular indices for lambda (blocks starting from (0,0))
r_inds_f1_block, c_inds_f1_block = np.tril_indices(f1_nv)
r_inds_f2_block, c_inds_f2_block = np.tril_indices(f2_nv)
# Repeat the factor 1 block for each level of factor 1
def solve(A, b, C, L, dims, proxqp=None, sigma=1.0, rho=1.0, **kwargs):
"""
Solves the SDP
min. < c, x >
s.t. A(x) = b
x >= 0
and its dual
max. -< b, y >
s.t. s >= 0.
c + A'(y) = s
Input arguments.
A is an N x M sparse matrix where N = sum_i ns[i]**2 and M = sum_j ms[j]
and ns and ms are the SDP variable sizes and constraint block lengths respectively.
The expression A(x) = b can be written as A.T*xtilde = b, where
xtilde is a stacked vector of vectorized versions of xi.
b is a stacked vector containing constraint vectors of
size m_i x 1.
C is a stacked vector containing vectorized 'd' matrices
c_k of size n_k**2 x 1, representing symmetric matrices.
L is an N X P sparse matrix, where L.T*X = 0 represents the consistency
constraints. If an index k appears in different cliques i,j, and
in converted form are indexed by it, jt, then L[it,l] = 1,
L[jt,l] = -1 for some l.
dims is a dictionary containing conic dimensions.
dims['l'] contains number of linear variables under nonnegativity constrant
dims['q'] contains a list of quadratic cone orders (not implemented!)
dims['s'] contains a list of semidefinite cone matrix orders
proxqp is either a function pointer to a prox implementation, or, if
the problem has block-diagonal correlative sparsity, a pointer
to the prox implementation of a single clique. The choices are:
proxqp_general : solves prox for general sparsity pattern
proxqp_clique : solves prox for a single dense clique with
only semidefinite variables.
proxqp_clique_SNL : solves prox for sensor network localization
problem
sigma is a nonnegative constant (step size)
rho is a nonnegative constaint between 0 and 2 (overrelaxation parameter)
In addition, the following paramters are optional:
maxiter : maximum number of iterations (default 100)
reltol : relative tolerance (default 0.01).
If rp < reltol and rd < reltol and iteration < maxiter,
solver breaks and returns current value.
adaptive : boolean toggle on whether adaptive step size should be
used. (default False)
mu, tau, tauscale : parameters for adaptive step size (see paper)
multiprocess : number of parallel processes (default 1).
if multiprocess = 1, no parallelization is used.
blockdiagonal : boolean toggle on whether problem has block diagonal
correlative sparsity. Note that even if the problem
does have block-diagonal correlative sparsity, if
this parameter is set to False, then general mode
is used. (default False)
verbose : toggle printout (default True)
log_cputime : toggle whether cputime should be logged.
The output is returned in a dictionary with the following files:
x : primal variable in stacked form (X = [x0, ..., x_{N-1}]) where
xk is the vectorized form of the nk x nk submatrix variable.
y, z : iterates in Spingarn's method
cputime, walltime : total cputime and walltime, respectively, spent in
main loop. If log_cputime is False, then cputime is
returned as 0.
primal, rprimal, rdual : evolution of primal optimal value, primal
residual, and dual residual (resp.)
sigma : evolution of step size sigma (changes if adaptive step size is used.)
"""
solvers.options['show_progress'] = False
maxiter = kwargs.get('maxiter', 100)
reltol = kwargs.get('reltol', 0.01)
adaptive = kwargs.get('adaptive', False)
mu = kwargs.get('mu', 2.0)
tau = kwargs.get('tau', 1.5)
multiprocess = kwargs.get('multiprocess', 1)
tauscale = kwargs.get('tauscale', 0.9)
blockdiagonal = kwargs.get('blockdiagonal', False)
verbose = kwargs.get('verbose', True)
log_cputime = kwargs.get('log_cputime', True)
if log_cputime:
try:
import psutil
except (ImportError):
assert False, "Python package psutil required to log cputime. Package can be downloaded at http://code.google.com/p/psutil/"
#format variables
nl, ns = dims['l'], dims['s']
C = C[nl:]
L = L[nl:, :]
As, bs = [], []
cons = []
offset = 0
for k in xrange(len(ns)):
Atmp = sparse(A[nl + offset:nl + offset + ns[k]**2, :])
J = list(set(list(Atmp.J)))
Atmp = Atmp[:, J]
if len(sparse(Atmp).V) == Atmp[:].size[0]: Atmp = matrix(Atmp)
else: Atmp = sparse(Atmp)
As.append(Atmp)
bs.append(b[J])
cons.append(J)
offset += ns[k]**2
if blockdiagonal:
if sum([len(c) for c in cons]) > len(b):
print "Problem does not have block-diagonal correlative sparsity. Switching to general mode."
blockdiagonal = False
#If not block-diagonal correlative sprasity, represent A as a list of lists:
# A[i][j] is a matrix (or spmatrix) if ith clique involves jth constraint block
#Otherwise, A is a list of matrices, where A[i] involves the ith clique and
#ith constraint block only.
if not blockdiagonal:
while sum([len(c) for c in cons]) > len(b):
tobreak = False
for i in xrange(len(cons)):
for j in xrange(i):
ci, cj = set(cons[i]), set(cons[j])
s1 = ci.intersection(cj)
if len(s1) > 0:
s2 = ci.difference(cj)
s3 = cj.difference(ci)
cons.append(list(s1))
if len(s2) > 0:
s2 = list(s2)
if not (s2 in cons): cons.append(s2)
if len(s3) > 0:
s3 = list(s3)
if not (s3 in cons): cons.append(s3)
cons.pop(i)
cons.pop(j)
tobreak = True
break
if tobreak: break
As, bs = [], []
for i in xrange(len(cons)):
J = cons[i]
bs.append(b[J])
Acol = []
offset = 0
for k in xrange(len(ns)):
Atmp = sparse(A[nl + offset:nl + offset + ns[k]**2, J])
if len(Atmp.V) == 0:
Acol.append(0)
elif len(Atmp.V) == Atmp[:].size[0]:
Acol.append(matrix(Atmp))
else:
Acol.append(Atmp)
offset += ns[k]**2
As.append(Acol)
ms = [len(i) for i in bs]
bs = matrix(bs)
meq = L.size[1]
if (not blockdiagonal) and multiprocess > 1:
print "Multiprocessing mode can only be used if correlative sparsity is block diagonal. Switching to sequential mode."
multiprocess = 1
assert rho > 0 and rho < 2, 'Overrelaxaton parameter (rho) must be (strictly) between 0 and 2'
# create routine for projecting on { x | L*x = 0 }
#{ x | L*x = 0 } -> P = I - L*(L.T*L)i *L.T
LTL = spmatrix([], [], [], (meq, meq))
offset = 0
for k in ns:
Lk = L[offset:offset + k**2, :]
base.syrk(Lk, LTL, trans='T', beta=1.0)
offset += k**2
LTLi = cholmod.symbolic(LTL, amd.order(LTL))
cholmod.numeric(LTL, LTLi)
#y = y - L*LTLi*L.T*y
nssq = sum(matrix([nsk**2 for nsk in ns]))
def proj(y, ip=True):
if not ip: y = +y
tmp = matrix(0.0, size=(meq, 1))
ypre = +y
base.gemv(L,y,tmp,trans='T',\
m = nssq, n = meq, beta = 1)
cholmod.solve(LTLi, tmp)
base.gemv(L,tmp,y,beta=1.0,alpha=-1.0,trans='N',\
m = nssq, n = meq)
if not ip: return y
time_to_solve = 0
#initialize variables
X = C * 0.0
Y = +X
Z = +X
dualS = +X
dualy = +b
PXZ = +X
proxargs = {
'C': C,
'A': As,
'b': bs,
'Z': Z,
'X': X,
'sigma': sigma,
'dualS': dualS,
'dualy': dualy,
'ns': ns,
'ms': ms,
'multiprocess': multiprocess
}
if blockdiagonal: proxqp = proxqp_blockdiagonal(proxargs, proxqp)
else: proxqp = proxqp_general
if log_cputime: utime = psutil.cpu_times()[0]
wtime = time.time()
primal = []
rpvec, rdvec = [], []
sigmavec = []
for it in xrange(maxiter):
pv, gap = proxqp(proxargs)
blas.copy(Z, Y)
blas.axpy(X, Y, alpha=-2.0)
proj(Y, ip=True)
#PXZ = sigma*(X-Z)
blas.copy(X, PXZ)
blas.scal(sigma, PXZ)
blas.axpy(Z, PXZ, alpha=-sigma)
#z = z + rho*(y-x)
blas.axpy(X, Y, alpha=1.0)
blas.axpy(Y, Z, alpha=-rho)
xzn = blas.nrm2(PXZ)
xn = blas.nrm2(X)
xyn = blas.nrm2(Y)
proj(PXZ, ip=True)
rdual = blas.nrm2(PXZ)
rpri = sqrt(abs(xyn**2 - rdual**2)) / sigma
if log_cputime: cputime = psutil.cpu_times()[0] - utime
else: cputime = 0
walltime = time.time() - wtime
if rpri / max(xn, 1.0) < reltol and rdual / max(1.0, xzn) < reltol:
break
rpvec.append(rpri / max(xn, 1.0))
rdvec.append(rdual / max(1.0, xzn))
primal.append(pv)
if adaptive:
if (rdual / xzn * mu < rpri / xn):
sigmanew = sigma * tau
elif (rpri / xn * mu < rdual / xzn):
sigmanew = sigma / tau
else:
sigmanew = sigma
if it % 10 == 0 and it > 0 and tau > 1.0:
tauscale *= 0.9
tau = 1 + (tau - 1) * tauscale
sigma = max(min(sigmanew, 10.0), 0.1)
sigmavec.append(sigma)
if verbose:
if log_cputime:
print "%d: primal = %e, gap = %e, (rp,rd) = (%e,%e), sigma = %f, (cputime,walltime) = (%f, %f)" % (
it, pv, gap, rpri / max(xn, 1.0), rdual / max(1.0, xzn),
sigma, cputime, walltime)
else:
print "%d: primal = %e, gap = %e, (rp,rd) = (%e,%e), sigma = %f, walltime = %f" % (
it, pv, gap, rpri / max(xn, 1.0), rdual / max(1.0, xzn),
sigma, walltime)
sol = {}
sol['x'] = X
sol['y'] = Y
sol['z'] = Z
sol['cputime'] = cputime
sol['walltime'] = walltime
sol['primal'] = primal
sol['rprimal'] = rpvec
sol['rdual'] = rdvec
sol['sigma'] = sigmavec
return sol
def factor(W, H=None, Df=None):
if F['firstcall']:
if type(G) is matrix:
F['Gs'] = matrix(0.0, G.size)
else:
F['Gs'] = spmatrix(0.0, G.I, G.J, G.size)
if mnl:
if type(Df) is matrix:
F['Dfs'] = matrix(0.0, Df.size)
else:
F['Dfs'] = spmatrix(0.0, Df.I, Df.J, Df.size)
if (mnl and type(Df) is matrix) or type(G) is matrix or \
type(H) is matrix:
F['S'] = matrix(0.0, (n, n))
F['K'] = matrix(0.0, (p, p))
else:
F['S'] = spmatrix([], [], [], (n, n), 'd')
F['Sf'] = None
if type(A) is matrix:
F['K'] = matrix(0.0, (p, p))
else:
F['K'] = spmatrix([], [], [], (p, p), 'd')
# Dfs = Wnl^{-1} * Df
if mnl:
base.gemm(spmatrix(W['dnli'], list(range(mnl)),
list(range(mnl))), Df, F['Dfs'], partial=True)
# Gs = Wl^{-1} * G.
base.gemm(spmatrix(W['di'], list(range(ml)), list(range(ml))),
G, F['Gs'], partial=True)
if F['firstcall']:
base.syrk(F['Gs'], F['S'], trans='T')
if mnl:
base.syrk(F['Dfs'], F['S'], trans='T', beta=1.0)
if H is not None:
F['S'] += H
try:
if type(F['S']) is matrix:
lapack.potrf(F['S'])
else:
F['Sf'] = cholmod.symbolic(F['S'])
cholmod.numeric(F['S'], F['Sf'])
except ArithmeticError:
F['singular'] = True
if type(A) is matrix and type(F['S']) is spmatrix:
F['S'] = matrix(0.0, (n, n))
base.syrk(F['Gs'], F['S'], trans='T')
if mnl:
base.syrk(F['Dfs'], F['S'], trans='T', beta=1.0)
base.syrk(A, F['S'], trans='T', beta=1.0)
if H is not None:
F['S'] += H
if type(F['S']) is matrix:
lapack.potrf(F['S'])
else:
F['Sf'] = cholmod.symbolic(F['S'])
cholmod.numeric(F['S'], F['Sf'])
F['firstcall'] = False
else:
base.syrk(F['Gs'], F['S'], trans='T', partial=True)
if mnl:
base.syrk(F['Dfs'], F['S'], trans='T', beta=1.0,
partial=True)
if H is not None:
F['S'] += H
if F['singular']:
base.syrk(A, F['S'], trans='T', beta=1.0, partial=True)
if type(F['S']) is matrix:
lapack.potrf(F['S'])
else:
cholmod.numeric(F['S'], F['Sf'])
if type(F['S']) is matrix:
# Asct := L^{-1}*A'. Factor K = Asct'*Asct.
if type(A) is matrix:
Asct = A.T
else:
Asct = matrix(A.T)
blas.trsm(F['S'], Asct)
blas.syrk(Asct, F['K'], trans='T')
lapack.potrf(F['K'])
else:
# Asct := L^{-1}*P*A'. Factor K = Asct'*Asct.
if type(A) is matrix:
Asct = A.T
cholmod.solve(F['Sf'], Asct, sys=7)
cholmod.solve(F['Sf'], Asct, sys=4)
blas.syrk(Asct, F['K'], trans='T')
lapack.potrf(F['K'])
else:
Asct = cholmod.spsolve(F['Sf'], A.T, sys=7)
Asct = cholmod.spsolve(F['Sf'], Asct, sys=4)
base.syrk(Asct, F['K'], trans='T')
Kf = cholmod.symbolic(F['K'])
cholmod.numeric(F['K'], Kf)
def solve(x, y, z):
# Solve
#
# [ H A' GG'*W^{-1} ] [ ux ] [ bx ]
# [ A 0 0 ] * [ uy ] = [ by ]
# [ W^{-T}*GG 0 -I ] [ W*uz ] [ W^{-T}*bz ]
#
# and return ux, uy, W*uz.
#
# If not F['singular']:
#
# K*uy = A * S^{-1} * ( bx + GG'*W^{-1}*W^{-T}*bz ) - by
# S*ux = bx + GG'*W^{-1}*W^{-T}*bz - A'*uy
# W*uz = W^{-T} * ( GG*ux - bz ).
#
# If F['singular']:
#
# K*uy = A * S^{-1} * ( bx + GG'*W^{-1}*W^{-T}*bz + A'*by )
# - by
# S*ux = bx + GG'*W^{-1}*W^{-T}*bz + A'*by - A'*y.
# W*uz = W^{-T} * ( GG*ux - bz ).
# z := W^{-1} * z = W^{-1} * bz
scale(z, W, trans='T', inverse='I')
# If not F['singular']:
# x := L^{-1} * P * (x + GGs'*z)
# = L^{-1} * P * (x + GG'*W^{-1}*W^{-T}*bz)
#
# If F['singular']:
# x := L^{-1} * P * (x + GGs'*z + A'*y))
# = L^{-1} * P * (x + GG'*W^{-1}*W^{-T}*bz + A'*y)
if mnl:
base.gemv(F['Dfs'], z, x, trans='T', beta=1.0)
base.gemv(F['Gs'], z, x, offsetx=mnl, trans='T',
beta=1.0)
if F['singular']:
base.gemv(A, y, x, trans='T', beta=1.0)
if type(F['S']) is matrix:
blas.trsv(F['S'], x)
else:
cholmod.solve(F['Sf'], x, sys=7)
cholmod.solve(F['Sf'], x, sys=4)
# y := K^{-1} * (Asc*x - y)
# = K^{-1} * (A * S^{-1} * (bx + GG'*W^{-1}*W^{-T}*bz) - by)
# (if not F['singular'])
# = K^{-1} * (A * S^{-1} * (bx + GG'*W^{-1}*W^{-T}*bz +
# A'*by) - by)
# (if F['singular']).
base.gemv(Asct, x, y, trans='T', beta=-1.0)
if type(F['K']) is matrix:
lapack.potrs(F['K'], y)
else:
cholmod.solve(Kf, y)
# x := P' * L^{-T} * (x - Asc'*y)
# = S^{-1} * (bx + GG'*W^{-1}*W^{-T}*bz - A'*y)
# (if not F['singular'])
# = S^{-1} * (bx + GG'*W^{-1}*W^{-T}*bz + A'*by - A'*y)
# (if F['singular'])
base.gemv(Asct, y, x, alpha=-1.0, beta=1.0)
if type(F['S']) is matrix:
blas.trsv(F['S'], x, trans='T')
else:
cholmod.solve(F['Sf'], x, sys=5)
cholmod.solve(F['Sf'], x, sys=8)
# W*z := GGs*x - z = W^{-T} * (GG*x - bz)
if mnl:
base.gemv(F['Dfs'], x, z, beta=-1.0)
base.gemv(F['Gs'], x, z, beta=-1.0, offsety=mnl)
return solve
def F(W):
for j in xrange(N):
# SVD R[j] = U[j] * diag(sig[j]) * Vt[j]
lapack.gesvd(+W['r'][j],
sv[j],
jobu='A',
jobvt='A',
U=U[j],
Vt=Vt[j])
# Vt[j] := diag(sig[j])^-1 * Vt[j]
for k in xrange(ns[j]):
blas.tbsv(sv[j], Vt[j], n=ns[j], k=0, ldA=1, offsetx=k * ns[j])
# Gamma[j] is an ns[j] x ns[j] symmetric matrix
#
# (sig[j] * sig[j]') ./ sqrt(1 + rho * (sig[j] * sig[j]').^2)
# S = sig[j] * sig[j]'
S = matrix(0.0, (ns[j], ns[j]))
blas.syrk(sv[j], S)
Gamma[j][:] = div(S, sqrt(1.0 + rho * S**2))[:]
symmetrize(Gamma[j], ns[j])
# As represents the scaled mapping
#
# As(x) = A(u * (Gamma .* x) * u')
# As'(y) = Gamma .* (u' * A'(y) * u)
#
# stored in a similar format as A, except that we use packed
# storage for the columns of As[i][j].
for i in xrange(M):
if (type(A[i][j]) is matrix) or (type(A[i][j]) is spmatrix):
# As[i][j][:,k] = vec(
# (U[j]' * mat( A[i][j][:,k] ) * U[j]) .* Gamma[j])
copy(A[i][j], As[i][j])
As[i][j] = matrix(As[i][j])
for k in xrange(ms[i]):
cngrnc(U[j],
As[i][j],
trans='T',
offsetx=k * (ns[j]**2),
n=ns[j])
blas.tbmv(Gamma[j],
As[i][j],
n=ns[j]**2,
k=0,
ldA=1,
offsetx=k * (ns[j]**2))
# pack As[i][j] in place
#pack_ip(As[i][j], ns[j])
for k in xrange(As[i][j].size[1]):
tmp = +As[i][j][:, k]
misc.pack2(tmp, {'l': 0, 'q': [], 's': [ns[j]]})
As[i][j][:, k] = tmp
else:
As[i][j] = 0.0
# H is an m times m block matrix with i, k block
#
# Hik = sum_j As[i,j]' * As[k,j]
#
# of size ms[i] x ms[k]. Hik = 0 if As[i,j] or As[k,j]
# are zero for all j
H = spmatrix([], [], [], (sum(ms), sum(ms)))
rowid = 0
for i in xrange(M):
colid = 0
for k in xrange(i + 1):
sparse_block = True
Hik = matrix(0.0, (ms[i], ms[k]))
for j in xrange(N):
if (type(As[i][j]) is matrix) and \
(type(As[k][j]) is matrix):
sparse_block = False
# Hik += As[i,j]' * As[k,j]
if i == k:
blas.syrk(As[i][j],
Hik,
trans='T',
beta=1.0,
k=ns[j] * (ns[j] + 1) / 2,
ldA=ns[j]**2)
else:
blas.gemm(As[i][j],
As[k][j],
Hik,
transA='T',
beta=1.0,
k=ns[j] * (ns[j] + 1) / 2,
ldA=ns[j]**2,
ldB=ns[j]**2)
if not (sparse_block):
H[rowid:rowid+ms[i], colid:colid+ms[k]] \
= sparse(Hik)
colid += ms[k]
rowid += ms[i]
HF = cholmod.symbolic(H)
cholmod.numeric(H, HF)
def solve(x, y, z):
"""
Returns solution of
rho * ux + A'(uy) - r^-T * uz * r^-1 = bx
A(ux) = by
-ux - r * uz * r' = bz.
On entry, x = bx, y = by, z = bz.
On exit, x = ux, y = uy, z = uz.
"""
# bz is a copy of z in the format of x
blas.copy(z, bz)
# x := x + rho * bz
# = bx + rho * bz
blas.axpy(bz, x, alpha=rho)
# x := Gamma .* (u' * x * u)
# = Gamma .* (u' * (bx + rho * bz) * u)
offsetj = 0
for j in xrange(N):
cngrnc(U[j], x, trans='T', offsetx=offsetj, n=ns[j])
blas.tbmv(Gamma[j], x, n=ns[j]**2, k=0, ldA=1, offsetx=offsetj)
offsetj += ns[j]**2
# y := y - As(x)
# := by - As( Gamma .* u' * (bx + rho * bz) * u)
blas.copy(x, xp)
offsetj = 0
for j in xrange(N):
misc.pack2(xp, {'l': offsetj, 'q': [], 's': [ns[j]]})
offsetj += ns[j]**2
offseti = 0
for i in xrange(M):
offsetj = 0
for j in xrange(N):
if type(As[i][j]) is matrix:
blas.gemv(As[i][j],
xp,
y,
trans='T',
alpha=-1.0,
beta=1.0,
m=ns[j] * (ns[j] + 1) / 2,
n=ms[i],
ldA=ns[j]**2,
offsetx=offsetj,
offsety=offseti)
offsetj += ns[j]**2
offseti += ms[i]
# y := -y - A(bz)
# = -by - A(bz) + As(Gamma .* (u' * (bx + rho * bz) * u)
Af(bz, y, alpha=-1.0, beta=-1.0)
# y := H^-1 * y
# = H^-1 ( -by - A(bz) + As(Gamma.* u'*(bx + rho*bz)*u) )
# = uy
cholmod.solve(HF, y)
# bz = Vt' * vz * Vt
# = uz where
# vz := Gamma .* ( As'(uy) - x )
# = Gamma .* ( As'(uy) - Gamma .* (u'*(bx + rho *bz)*u) )
# = Gamma.^2 .* ( u' * (A'(uy) - bx - rho * bz) * u ).
blas.copy(x, xp)
offsetj = 0
for j in xrange(N):
# xp is -x[j] = -Gamma .* (u' * (bx + rho*bz) * u)
# in packed storage
misc.pack2(xp, {'l': offsetj, 'q': [], 's': [ns[j]]})
offsetj += ns[j]**2
blas.scal(-1.0, xp)
offsetj = 0
for j in xrange(N):
# xp += As'(uy)
offseti = 0
for i in xrange(M):
if type(As[i][j]) is matrix:
blas.gemv(As[i][j], y, xp, alpha = 1.0,
beta = 1.0, m = ns[j]*(ns[j]+1)/2, \
n = ms[i],ldA = ns[j]**2, \
offsetx = offseti, offsety = offsetj)
offseti += ms[i]
# bz[j] is xp unpacked and multiplied with Gamma
#unpack(xp, bz[j], ns[j])
misc.unpack(xp,
bz, {
'l': 0,
'q': [],
's': [ns[j]]
},
offsetx=offsetj,
offsety=offsetj)
blas.tbmv(Gamma[j],
bz,
n=ns[j]**2,
k=0,
ldA=1,
offsetx=offsetj)
# bz = Vt' * bz * Vt
# = uz
cngrnc(Vt[j], bz, trans='T', offsetx=offsetj, n=ns[j])
symmetrize(bz, ns[j], offset=offsetj)
offsetj += ns[j]**2
# x = -bz - r * uz * r'
blas.copy(z, x)
blas.copy(bz, z)
offsetj = 0
for j in xrange(N):
cngrnc(+W['r'][j], bz, offsetx=offsetj, n=ns[j])
offsetj += ns[j]**2
blas.axpy(bz, x)
blas.scal(-1.0, x)
return solve
from cvxopt import matrix, spmatrix, cholmod A = spmatrix([10, 3, 5, -2, 5, 2], [0, 2, 1, 3, 2, 3], [0, 0, 1, 1, 2, 3]) X = matrix(range(8), (4,2), 'd') F = cholmod.symbolic(A) cholmod.numeric(A, F) cholmod.solve(F, X) print(X) P = cvxopt.matrix(P) print(cvxopt.matrix(list(map(lambda x: x != 1, abs(P))), P.size))
def covsel(Y):
"""
Returns the solution of
minimize -log det K + tr(KY)
subject to K_ij = 0 if (i,j) not in zip(I, J).
Y is a symmetric sparse matrix with nonzero diagonal elements.
I = Y.I, J = Y.J.
"""
cholmod.options['supernodal'] = 2
I, J = Y.I, Y.J
n, m = Y.size[0], len(I)
# non-zero positions for one-argument indexing
N = I + J*n
# position of diagonal elements
D = [ k for k in range(m) if I[k]==J[k] ]
# starting point: symmetric identity with nonzero pattern I,J
K = spmatrix(0.0, I, J)
K[::n+1] = 1.0
# Kn is used in the line search
Kn = spmatrix(0.0, I, J)
# symbolic factorization of K
F = cholmod.symbolic(K)
# Kinv will be the inverse of K
Kinv = matrix(0.0, (n,n))
for iters in range(100):
# numeric factorization of K
cholmod.numeric(K, F)
d = cholmod.diag(F)
# compute Kinv by solving K*X = I
Kinv[:] = 0.0
Kinv[::n+1] = 1.0
cholmod.solve(F, Kinv)
# solve Newton system
grad = 2 * (Y.V - Kinv[N])
hess = 2 * ( mul(Kinv[I,J], Kinv[J,I]) +
mul(Kinv[I,I], Kinv[J,J]) )
v = -grad
lapack.posv(hess,v)
# stopping criterion
sqntdecr = -blas.dot(grad,v)
print("Newton decrement squared:%- 7.5e" %sqntdecr)
if (sqntdecr < 1e-12):
print("number of iterations: %d" %(iters+1))
break
# line search
dx = +v
dx[D] *= 2
f = -2.0*sum(log(d)) # f = -log det K
s = 1
for lsiter in range(50):
Kn.V = K.V + s*dx
try:
cholmod.numeric(Kn, F)
except ArithmeticError:
s *= 0.5
else:
d = cholmod.diag(F)
fn = -2.0 * sum(log(d)) + 2*s*blas.dot(v,Y.V)
if (fn < f - 0.01*s*sqntdecr): break
else: s *= 0.5
K.V = Kn.V
return K
def solve_phase1(self,kktsolver='chol',MM = 1e5):
"""
Solves primal Phase I problem using the feasible
start solver.
Returns primal feasible X.
"""
from cvxopt import cholmod, amd
k = 1e-3
# compute Schur complement matrix
Id = [i*(self.n+1) for i in range(self.n)]
As = self._A[:,1:]
As[Id,:] /= sqrt(2.0)
M = spmatrix([],[],[],(self.m,self.m))
base.syrk(As,M,trans='T')
u = +self.b
# compute least-norm solution
F = cholmod.symbolic(M)
cholmod.numeric(M,F)
cholmod.solve(F,u)
x = 0.5*self._A[:,1:]*u
X0 = spmatrix(x[self.V[:].I],self.V.I,self.V.J,(self.n,self.n))
# test feasibility
p = amd.order(self.V)
#Xc,Nf = chompack.embed(X0,p)
#E = chompack.project(Xc,spmatrix(1.0,range(self.n),range(self.n)))
symb = chompack.symbolic(self.V,p)
Xc = chompack.cspmatrix(symb) + X0
try:
# L = chompack.completion(Xc)
L = Xc.copy()
chompack.completion(L)
# least-norm solution is feasible
return X0,None
except:
pass
# create Phase I SDP object
trA = matrix(0.0,(self.m+1,1))
e = matrix(1.0,(self.n,1))
Aa = self._A[Id,1:]
base.gemv(Aa,e,trA,trans='T')
trA[-1] = MM
P1 = SDP()
P1._A = misc.phase1_sdp(self._A,trA)
P1._b = matrix([self.b-k*trA[:self.m],MM])
P1._agg_sparsity()
# find feasible starting point for Phase I problem
tMIN = 0.0
tMAX = 1.0
while True:
t = (tMIN+tMAX)/2.0
#Xt = chompack.copy(Xc)
#chompack.axpy(E,Xt,t)
Xt = Xc.copy() + spmatrix(t,list(range(self.n)),list(range(self.n)))
try:
# L = chompack.completion(Xt)
L = Xt.copy()
chompack.completion(L)
tMAX = t
if tMAX - tMIN < 1e-1:
break
except:
tMAX *= 2.0
tMIN = t
tt = t + 1.0
U = X0 + spmatrix(tt,list(range(self.n,)),list(range(self.n)))
trU = sum(U[:][Id])
Z0 = spdiag([U,spmatrix([tt+k,MM-trU],[0,1],[0,1],(2,2))])
sol = P1.solve_feas(primalstart = {'x':Z0}, kktsolver = kktsolver)
s = sol['x'][-2,-2] - k
if s > 0:
return None,P1
else:
sol.pop('y')
sol.pop('s')
X0 = sol.pop('x')[:self.n,:self.n]\
- spmatrix(s,list(range(self.n)),list(range(self.n)))
return X0,sol
def solve_phase1(self, kktsolver='chol', MM=1e5):
"""
Solves primal Phase I problem using the feasible
start solver.
Returns primal feasible X.
"""
from cvxopt import cholmod, amd
k = 1e-3
# compute Schur complement matrix
Id = [i * (self.n + 1) for i in range(self.n)]
As = self._A[:, 1:]
As[Id, :] /= sqrt(2.0)
M = spmatrix([], [], [], (self.m, self.m))
base.syrk(As, M, trans='T')
u = +self.b
# compute least-norm solution
F = cholmod.symbolic(M)
cholmod.numeric(M, F)
cholmod.solve(F, u)
x = 0.5 * self._A[:, 1:] * u
X0 = spmatrix(x[self.V[:].I], self.V.I, self.V.J, (self.n, self.n))
# test feasibility
p = amd.order(self.V)
#Xc,Nf = chompack.embed(X0,p)
#E = chompack.project(Xc,spmatrix(1.0,range(self.n),range(self.n)))
symb = chompack.symbolic(self.V, p)
Xc = chompack.cspmatrix(symb) + X0
try:
# L = chompack.completion(Xc)
L = Xc.copy()
chompack.completion(L)
# least-norm solution is feasible
return X0
except:
pass
# create Phase I SDP object
trA = matrix(0.0, (self.m + 1, 1))
e = matrix(1.0, (self.n, 1))
Aa = self._A[Id, 1:]
base.gemv(Aa, e, trA, trans='T')
trA[-1] = MM
P1 = SDP()
P1._A = misc.phase1_sdp(self._A, trA)
P1._b = matrix([self.b - k * trA[:self.m], MM])
P1._agg_sparsity()
# find feasible starting point for Phase I problem
tMIN = 0.0
tMAX = 1.0
while True:
t = (tMIN + tMAX) / 2.0
#Xt = chompack.copy(Xc)
#chompack.axpy(E,Xt,t)
Xt = Xc.copy() + spmatrix(t, range(self.n), range(self.n))
try:
# L = chompack.completion(Xt)
L = Xt.copy()
chompack.completion(L)
tMAX = t
if tMAX - tMIN < 1e-1:
break
except:
tMAX *= 2.0
tMIN = t
tt = t + 1.0
U = X0 + spmatrix(tt, range(self.n, ), range(self.n))
trU = sum(U[:][Id])
Z0 = spdiag([U, spmatrix([tt + k, MM - trU], [0, 1], [0, 1], (2, 2))])
sol = P1.solve_feas(primalstart={'x': Z0}, kktsolver=kktsolver)
s = sol['x'][-2, -2] - k
if s > 0:
return None, P1
else:
sol.pop('y')
sol.pop('s')
X0 = sol.pop('x')[:self.n,:self.n]\
- spmatrix(s,range(self.n),range(self.n))
return X0, sol