def __cngrnc(r, x, alpha = 1.0, trans = 'N', offsetx = 0): """ In-place congruence transformation x := alpha * r * x * r' if trans = 'N'. x := alpha * r' * x * r if trans = 'T'. r is a square n x n-matrix. x is a square n x n-matrix or n^2-vector. """ n = r.size[0] # Scale diagonal of x by 1/2. blas.scal(0.5, x, inc = n+1, offset = offsetx) # a := r*tril(x) if trans is 'N', a := tril(x)*r if trans is 'T'. a = +r if trans == 'N': blas.trmm(x, a, side = 'R', m = n, n = n, ldA = n, ldB = n, offsetA = offsetx) else: blas.trmm(x, a, side = 'L', m = n, n = n, ldA = n, ldB = n, offsetA = offsetx) # x := alpha * (a * r' + r * a') # = alpha * r * (tril(x) + tril(x)') * r' if trans is 'N'. # x := alpha * (a' * r + r' * a) # = alpha * r' * (tril(x)' + tril(x)) * r if trans = 'T'. blas.syr2k(r, a, x, trans = trans, alpha = alpha, n = n, k = n, ldB = n, ldC = n, offsetC = offsetx)
def cngrnc(r, x, alpha = 1.0): """ Congruence transformation x := alpha * r'*x*r. r and x are square matrices. """ # Scale diagonal of x by 1/2. x[::n+1] *= 0.5 # a := tril(x)*r a = +r tx = matrix(x, (n,n)) blas.trmm(tx, a, side='L') # x := alpha*(a*r' + r*a') blas.syr2k(r, a, tx, trans = 'T', alpha = alpha) x[:] = tx[:]
def cngrnc(r, x, alpha = 1.0): """ Congruence transformation x := alpha * r'*x*r. r and x are square matrices. """ # Scale diagonal of x by 1/2. x[::n+1] *= 0.5 # a := tril(x)*r a = +r tx = matrix(x, (n,n)) blas.trmm(tx, a, side = 'L') # x := alpha*(a*r' + r*a') blas.syr2k(r, a, tx, trans = 'T', alpha = alpha) x[:] = tx[:]
def __cngrnc(r, x, alpha=1.0, trans='N', offsetx=0): """ In-place congruence transformation x := alpha * r * x * r' if trans = 'N'. x := alpha * r' * x * r if trans = 'T'. r is a square n x n-matrix. x is a square n x n-matrix or n^2-vector. """ n = r.size[0] # Scale diagonal of x by 1/2. blas.scal(0.5, x, inc=n + 1, offset=offsetx) # a := r*tril(x) if trans is 'N', a := tril(x)*r if trans is 'T'. a = +r if trans == 'N': blas.trmm(x, a, side='R', m=n, n=n, ldA=n, ldB=n, offsetA=offsetx) else: blas.trmm(x, a, side='L', m=n, n=n, ldA=n, ldB=n, offsetA=offsetx) # x := alpha * (a * r' + r * a') # = alpha * r * (tril(x) + tril(x)') * r' if trans is 'N'. # x := alpha * (a' * r + r' * a) # = alpha * r' * (tril(x)' + tril(x)) * r if trans = 'T'. blas.syr2k(r, a, x, trans=trans, alpha=alpha, n=n, k=n, ldB=n, ldC=n, offsetC=offsetx)
def cngrnc(r, x, n, xstart=0, alpha=1.0): """ Congruence transformation x := alpha * r'*x*r. r is a square matrix, and x is a symmetric matrix. """ # return alpha*r.T*matrix(x, (n,n))*r # Scale diagonal of x by 1/2. nsqr = n * n xend = xstart + nsqr x[xstart:xend:n + 1] *= 0.5 # a := tril(x)*r a = +r tx = matrix(x[xstart:xend], (n, n)) blas.trmm(tx, a, side='L') # x := alpha*(a*r' + r*a') blas.syr2k(r, a, tx, trans='T', alpha=alpha) x[xstart:xend] = tx[:]
def fsolve(x, y, z): """ Solves the system of equations [ 0 G'*W^{-1} ] [ ux ] = [ bx ] [ G -W' ] [ uz ] [ bz ] """ # Compute bx := bx + G'*W^{-1}*W^{-T}*bz v = matrix(0., (N, 1)) for i in range(N): blas.symv(z, rr, v, ldA=N, offsetA=1, n=N, offsetx=N * i) x[i] += blas.dot(rr, v, n=N, offsetx=N * i) blas.symv(z, q, v, ldA=N, offsetA=1, n=N) x[N] += blas.dot(q, v) + z[0] * W['di'][0]**2 # Solve G'*W^{-1}*W^{-T}*G*ux = bx lapack.potrs(H, x) # Compute bz := -W^{-T}*(bz-G*ux) # z -= G*x z[1::N + 1] -= x[:-1] z -= x[-1] # Apply scaling z[0] *= -W['di'][0] blas.scal(0.5, z, n=N, offset=1, inc=N + 1) tmp = +r blas.trmm(z, tmp, ldA=N, offsetA=1, n=N, m=N) blas.syr2k(r, tmp, z, trans='T', offsetC=1, ldC=N, n=N, k=N, alpha=-1.0)
def f(x, y, z): """ Solve C * ux + G' * uzl - 2*A'(uzs21) = bx -uzs11 = bX1 -uzs22 = bX2 G * ux - D^2 * uzl = bzl [ -uX1 -A(ux)' ] [ uzs11 uzs21' ] [ ] - T * [ ] * T = bzs. [ -A(ux) -uX2 ] [ uzs21 uzs22 ] On entry, x = (bx, bX1, bX2) and z = [ bzl; bzs[:] ]. On exit, x = (ux, uX1, uX2) and z = [ D*uzl; (r'*uzs*r)[:] ]. Define X = uzs21, Z = T * uzs * T: C * ux + G' * uzl - 2*A'(X) = bx [ 0 X' ] [ bX1 0 ] T * [ ] * T - Z = T * [ ] * T [ X 0 ] [ 0 bX2 ] G * ux - D^2 * uzl = bzl [ -uX1 -A(ux)' ] [ Z11 Z21' ] [ ] - [ ] = bzs [ -A(ux) -uX2 ] [ Z21 Z22 ] Return x = (ux, uX1, uX2), z = [ D*uzl; (rti'*Z*rti)[:] ]. We use the congruence transformation [ V1 0 ] [ T11 T21' ] [ V1' 0 ] [ I S' ] [ ] [ ] [ ] = [ ] [ 0 V2' ] [ T21 T22 ] [ 0 V2 ] [ S I ] and the factorization X + S * X' * S = L( L'(X) ) to write this as C * ux + G' * uzl - 2*A'(X) = bx L'(V2^-1 * X * V1^-1) - L^-1(V2' * Z21 * V1') = bX G * ux - D^2 * uzl = bzl [ -uX1 -A(ux)' ] [ Z11 Z21' ] [ ] - [ ] = bzs, [ -A(ux) -uX2 ] [ Z21 Z22 ] or C * ux + Gs' * uuzl - 2*As'(XX) = bx XX - ZZ21 = bX Gs * ux - uuzl = D^-1 * bzl -As(ux) - ZZ21 = bbzs_21 -uX1 - Z11 = bzs_11 -uX2 - Z22 = bzs_22 if we introduce scaled variables uuzl = D * uzl XX = L'(V2^-1 * X * V1^-1) = L'(V2^-1 * uzs21 * V1^-1) ZZ21 = L^-1(V2' * Z21 * V1') and define bbzs_21 = L^-1(V2' * bzs_21 * V1') [ bX1 0 ] bX = L^-1( V2' * (T * [ ] * T)_21 * V1'). [ 0 bX2 ] Eliminating Z21 gives C * ux + Gs' * uuzl - 2*As'(XX) = bx Gs * ux - uuzl = D^-1 * bzl -As(ux) - XX = bbzs_21 - bX -uX1 - Z11 = bzs_11 -uX2 - Z22 = bzs_22 and eliminating uuzl and XX gives H * ux = bx + Gs' * D^-1 * bzl + 2*As'(bX - bbzs_21) Gs * ux - uuzl = D^-1 * bzl -As(ux) - XX = bbzs_21 - bX -uX1 - Z11 = bzs_11 -uX2 - Z22 = bzs_22. In summary, we can use the following algorithm: 1. bXX := bX - bbzs21 [ bX1 0 ] = L^-1( V2' * ((T * [ ] * T)_21 - bzs_21) * V1') [ 0 bX2 ] 2. Solve H * ux = bx + Gs' * D^-1 * bzl + 2*As'(bXX). 3. From ux, compute uuzl = Gs*ux - D^-1 * bzl and X = V2 * L^-T(-As(ux) + bXX) * V1. 4. Return ux, uuzl, rti' * Z * rti = r' * [ -bX1, X'; X, -bX2 ] * r and uX1 = -Z11 - bzs_11, uX2 = -Z22 - bzs_22. """ # Save bzs_11, bzs_22, bzs_21. lapack.lacpy(z, bz11, uplo = 'L', m = q, n = q, ldA = p+q, offsetA = m) lapack.lacpy(z, bz21, m = p, n = q, ldA = p+q, offsetA = m+q) lapack.lacpy(z, bz22, uplo = 'L', m = p, n = p, ldA = p+q, offsetA = m + (p+q+1)*q) # zl := D^-1 * zl # = D^-1 * bzl blas.tbmv(W['di'], z, n = m, k = 0, ldA = 1) # zs := r' * [ bX1, 0; 0, bX2 ] * r. # zs := [ bX1, 0; 0, bX2 ] blas.scal(0.0, z, offset = m) lapack.lacpy(x[1], z, uplo = 'L', m = q, n = q, ldB = p+q, offsetB = m) lapack.lacpy(x[2], z, uplo = 'L', m = p, n = p, ldB = p+q, offsetB = m + (p+q+1)*q) # scale diagonal of zs by 1/2 blas.scal(0.5, z, inc = p+q+1, offset = m) # a := tril(zs)*r blas.copy(r, a) blas.trmm(z, a, side = 'L', m = p+q, n = p+q, ldA = p+q, ldB = p+q, offsetA = m) # zs := a'*r + r'*a blas.syr2k(r, a, z, trans = 'T', n = p+q, k = p+q, ldB = p+q, ldC = p+q, offsetC = m) # bz21 := L^-1( V2' * ((r * zs * r')_21 - bz21) * V1') # # [ bX1 0 ] # = L^-1( V2' * ((T * [ ] * T)_21 - bz21) * V1'). # [ 0 bX2 ] # a = [ r21 r22 ] * z # = [ r21 r22 ] * r' * [ bX1, 0; 0, bX2 ] * r # = [ T21 T22 ] * [ bX1, 0; 0, bX2 ] * r blas.symm(z, r, a, side = 'R', m = p, n = p+q, ldA = p+q, ldC = p+q, offsetB = q) # bz21 := -bz21 + a * [ r11, r12 ]' # = -bz21 + (T * [ bX1, 0; 0, bX2 ] * T)_21 blas.gemm(a, r, bz21, transB = 'T', m = p, n = q, k = p+q, beta = -1.0, ldA = p+q, ldC = p) # bz21 := V2' * bz21 * V1' # = V2' * (-bz21 + (T*[bX1, 0; 0, bX2]*T)_21) * V1' blas.gemm(V2, bz21, tmp, transA = 'T', m = p, n = q, k = p, ldB = p) blas.gemm(tmp, V1, bz21, transB = 'T', m = p, n = q, k = q, ldC = p) # bz21[:] := D * (I-P) * bz21[:] # = L^-1 * bz21[:] # = bXX[:] blas.copy(bz21, tmp) base.gemv(P, bz21, tmp, alpha = -1.0, beta = 1.0) base.gemv(D, tmp, bz21) # Solve H * ux = bx + Gs' * D^-1 * bzl + 2*As'(bXX). # x[0] := x[0] + Gs'*zl + 2*As'(bz21) # = bx + G' * D^-1 * bzl + 2 * As'(bXX) blas.gemv(Gs, z, x[0], trans = 'T', alpha = 1.0, beta = 1.0) blas.gemv(As, bz21, x[0], trans = 'T', alpha = 2.0, beta = 1.0) # x[0] := H \ x[0] # = ux lapack.potrs(H, x[0]) # uuzl = Gs*ux - D^-1 * bzl blas.gemv(Gs, x[0], z, alpha = 1.0, beta = -1.0) # bz21 := V2 * L^-T(-As(ux) + bz21) * V1 # = X blas.gemv(As, x[0], bz21, alpha = -1.0, beta = 1.0) blas.tbsv(DV, bz21, n = p*q, k = 0, ldA = 1) blas.copy(bz21, tmp) base.gemv(P, tmp, bz21, alpha = -1.0, beta = 1.0, trans = 'T') blas.gemm(V2, bz21, tmp) blas.gemm(tmp, V1, bz21) # zs := -zs + r' * [ 0, X'; X, 0 ] * r # = r' * [ -bX1, X'; X, -bX2 ] * r. # a := bz21 * [ r11, r12 ] # = X * [ r11, r12 ] blas.gemm(bz21, r, a, m = p, n = p+q, k = q, ldA = p, ldC = p+q) # z := -z + [ r21, r22 ]' * a + a' * [ r21, r22 ] # = rti' * uzs * rti blas.syr2k(r, a, z, trans = 'T', beta = -1.0, n = p+q, k = p, offsetA = q, offsetC = m, ldB = p+q, ldC = p+q) # uX1 = -Z11 - bzs_11 # = -(r*zs*r')_11 - bzs_11 # uX2 = -Z22 - bzs_22 # = -(r*zs*r')_22 - bzs_22 blas.copy(bz11, x[1]) blas.copy(bz22, x[2]) # scale diagonal of zs by 1/2 blas.scal(0.5, z, inc = p+q+1, offset = m) # a := r*tril(zs) blas.copy(r, a) blas.trmm(z, a, side = 'R', m = p+q, n = p+q, ldA = p+q, ldB = p+q, offsetA = m) # x[1] := -x[1] - a[:q,:] * r[:q, :]' - r[:q,:] * a[:q,:]' # = -bzs_11 - (r*zs*r')_11 blas.syr2k(a, r, x[1], n = q, alpha = -1.0, beta = -1.0) # x[2] := -x[2] - a[q:,:] * r[q:, :]' - r[q:,:] * a[q:,:]' # = -bzs_22 - (r*zs*r')_22 blas.syr2k(a, r, x[2], n = p, alpha = -1.0, beta = -1.0, offsetA = q, offsetB = q) # scale diagonal of zs by 1/2 blas.scal(2.0, z, inc = p+q+1, offset = m)
def f(x, y, z): """ Solve C * ux + G' * uzl - 2*A'(uzs21) = bx -uzs11 = bX1 -uzs22 = bX2 G * ux - D^2 * uzl = bzl [ -uX1 -A(ux)' ] [ uzs11 uzs21' ] [ ] - T * [ ] * T = bzs. [ -A(ux) -uX2 ] [ uzs21 uzs22 ] On entry, x = (bx, bX1, bX2) and z = [ bzl; bzs[:] ]. On exit, x = (ux, uX1, uX2) and z = [ D*uzl; (r'*uzs*r)[:] ]. Define X = uzs21, Z = T * uzs * T: C * ux + G' * uzl - 2*A'(X) = bx [ 0 X' ] [ bX1 0 ] T * [ ] * T - Z = T * [ ] * T [ X 0 ] [ 0 bX2 ] G * ux - D^2 * uzl = bzl [ -uX1 -A(ux)' ] [ Z11 Z21' ] [ ] - [ ] = bzs [ -A(ux) -uX2 ] [ Z21 Z22 ] Return x = (ux, uX1, uX2), z = [ D*uzl; (rti'*Z*rti)[:] ]. We use the congruence transformation [ V1 0 ] [ T11 T21' ] [ V1' 0 ] [ I S' ] [ ] [ ] [ ] = [ ] [ 0 V2' ] [ T21 T22 ] [ 0 V2 ] [ S I ] and the factorization X + S * X' * S = L( L'(X) ) to write this as C * ux + G' * uzl - 2*A'(X) = bx L'(V2^-1 * X * V1^-1) - L^-1(V2' * Z21 * V1') = bX G * ux - D^2 * uzl = bzl [ -uX1 -A(ux)' ] [ Z11 Z21' ] [ ] - [ ] = bzs, [ -A(ux) -uX2 ] [ Z21 Z22 ] or C * ux + Gs' * uuzl - 2*As'(XX) = bx XX - ZZ21 = bX Gs * ux - uuzl = D^-1 * bzl -As(ux) - ZZ21 = bbzs_21 -uX1 - Z11 = bzs_11 -uX2 - Z22 = bzs_22 if we introduce scaled variables uuzl = D * uzl XX = L'(V2^-1 * X * V1^-1) = L'(V2^-1 * uzs21 * V1^-1) ZZ21 = L^-1(V2' * Z21 * V1') and define bbzs_21 = L^-1(V2' * bzs_21 * V1') [ bX1 0 ] bX = L^-1( V2' * (T * [ ] * T)_21 * V1'). [ 0 bX2 ] Eliminating Z21 gives C * ux + Gs' * uuzl - 2*As'(XX) = bx Gs * ux - uuzl = D^-1 * bzl -As(ux) - XX = bbzs_21 - bX -uX1 - Z11 = bzs_11 -uX2 - Z22 = bzs_22 and eliminating uuzl and XX gives H * ux = bx + Gs' * D^-1 * bzl + 2*As'(bX - bbzs_21) Gs * ux - uuzl = D^-1 * bzl -As(ux) - XX = bbzs_21 - bX -uX1 - Z11 = bzs_11 -uX2 - Z22 = bzs_22. In summary, we can use the following algorithm: 1. bXX := bX - bbzs21 [ bX1 0 ] = L^-1( V2' * ((T * [ ] * T)_21 - bzs_21) * V1') [ 0 bX2 ] 2. Solve H * ux = bx + Gs' * D^-1 * bzl + 2*As'(bXX). 3. From ux, compute uuzl = Gs*ux - D^-1 * bzl and X = V2 * L^-T(-As(ux) + bXX) * V1. 4. Return ux, uuzl, rti' * Z * rti = r' * [ -bX1, X'; X, -bX2 ] * r and uX1 = -Z11 - bzs_11, uX2 = -Z22 - bzs_22. """ # Save bzs_11, bzs_22, bzs_21. lapack.lacpy(z, bz11, uplo='L', m=q, n=q, ldA=p + q, offsetA=m) lapack.lacpy(z, bz21, m=p, n=q, ldA=p + q, offsetA=m + q) lapack.lacpy(z, bz22, uplo='L', m=p, n=p, ldA=p + q, offsetA=m + (p + q + 1) * q) # zl := D^-1 * zl # = D^-1 * bzl blas.tbmv(W['di'], z, n=m, k=0, ldA=1) # zs := r' * [ bX1, 0; 0, bX2 ] * r. # zs := [ bX1, 0; 0, bX2 ] blas.scal(0.0, z, offset=m) lapack.lacpy(x[1], z, uplo='L', m=q, n=q, ldB=p + q, offsetB=m) lapack.lacpy(x[2], z, uplo='L', m=p, n=p, ldB=p + q, offsetB=m + (p + q + 1) * q) # scale diagonal of zs by 1/2 blas.scal(0.5, z, inc=p + q + 1, offset=m) # a := tril(zs)*r blas.copy(r, a) blas.trmm(z, a, side='L', m=p + q, n=p + q, ldA=p + q, ldB=p + q, offsetA=m) # zs := a'*r + r'*a blas.syr2k(r, a, z, trans='T', n=p + q, k=p + q, ldB=p + q, ldC=p + q, offsetC=m) # bz21 := L^-1( V2' * ((r * zs * r')_21 - bz21) * V1') # # [ bX1 0 ] # = L^-1( V2' * ((T * [ ] * T)_21 - bz21) * V1'). # [ 0 bX2 ] # a = [ r21 r22 ] * z # = [ r21 r22 ] * r' * [ bX1, 0; 0, bX2 ] * r # = [ T21 T22 ] * [ bX1, 0; 0, bX2 ] * r blas.symm(z, r, a, side='R', m=p, n=p + q, ldA=p + q, ldC=p + q, offsetB=q) # bz21 := -bz21 + a * [ r11, r12 ]' # = -bz21 + (T * [ bX1, 0; 0, bX2 ] * T)_21 blas.gemm(a, r, bz21, transB='T', m=p, n=q, k=p + q, beta=-1.0, ldA=p + q, ldC=p) # bz21 := V2' * bz21 * V1' # = V2' * (-bz21 + (T*[bX1, 0; 0, bX2]*T)_21) * V1' blas.gemm(V2, bz21, tmp, transA='T', m=p, n=q, k=p, ldB=p) blas.gemm(tmp, V1, bz21, transB='T', m=p, n=q, k=q, ldC=p) # bz21[:] := D * (I-P) * bz21[:] # = L^-1 * bz21[:] # = bXX[:] blas.copy(bz21, tmp) base.gemv(P, bz21, tmp, alpha=-1.0, beta=1.0) base.gemv(D, tmp, bz21) # Solve H * ux = bx + Gs' * D^-1 * bzl + 2*As'(bXX). # x[0] := x[0] + Gs'*zl + 2*As'(bz21) # = bx + G' * D^-1 * bzl + 2 * As'(bXX) blas.gemv(Gs, z, x[0], trans='T', alpha=1.0, beta=1.0) blas.gemv(As, bz21, x[0], trans='T', alpha=2.0, beta=1.0) # x[0] := H \ x[0] # = ux lapack.potrs(H, x[0]) # uuzl = Gs*ux - D^-1 * bzl blas.gemv(Gs, x[0], z, alpha=1.0, beta=-1.0) # bz21 := V2 * L^-T(-As(ux) + bz21) * V1 # = X blas.gemv(As, x[0], bz21, alpha=-1.0, beta=1.0) blas.tbsv(DV, bz21, n=p * q, k=0, ldA=1) blas.copy(bz21, tmp) base.gemv(P, tmp, bz21, alpha=-1.0, beta=1.0, trans='T') blas.gemm(V2, bz21, tmp) blas.gemm(tmp, V1, bz21) # zs := -zs + r' * [ 0, X'; X, 0 ] * r # = r' * [ -bX1, X'; X, -bX2 ] * r. # a := bz21 * [ r11, r12 ] # = X * [ r11, r12 ] blas.gemm(bz21, r, a, m=p, n=p + q, k=q, ldA=p, ldC=p + q) # z := -z + [ r21, r22 ]' * a + a' * [ r21, r22 ] # = rti' * uzs * rti blas.syr2k(r, a, z, trans='T', beta=-1.0, n=p + q, k=p, offsetA=q, offsetC=m, ldB=p + q, ldC=p + q) # uX1 = -Z11 - bzs_11 # = -(r*zs*r')_11 - bzs_11 # uX2 = -Z22 - bzs_22 # = -(r*zs*r')_22 - bzs_22 blas.copy(bz11, x[1]) blas.copy(bz22, x[2]) # scale diagonal of zs by 1/2 blas.scal(0.5, z, inc=p + q + 1, offset=m) # a := r*tril(zs) blas.copy(r, a) blas.trmm(z, a, side='R', m=p + q, n=p + q, ldA=p + q, ldB=p + q, offsetA=m) # x[1] := -x[1] - a[:q,:] * r[:q, :]' - r[:q,:] * a[:q,:]' # = -bzs_11 - (r*zs*r')_11 blas.syr2k(a, r, x[1], n=q, alpha=-1.0, beta=-1.0) # x[2] := -x[2] - a[q:,:] * r[q:, :]' - r[q:,:] * a[q:,:]' # = -bzs_22 - (r*zs*r')_22 blas.syr2k(a, r, x[2], n=p, alpha=-1.0, beta=-1.0, offsetA=q, offsetB=q) # scale diagonal of zs by 1/2 blas.scal(2.0, z, inc=p + q + 1, offset=m)
def scale(x, W, trans='N', inverse='N'): """ Applies Nesterov-Todd scaling or its inverse. Computes x := W*x (trans is 'N', inverse = 'N') x := W^T*x (trans is 'T', inverse = 'N') x := W^{-1}*x (trans is 'N', inverse = 'I') x := W^{-T}*x (trans is 'T', inverse = 'I'). x is a dense 'd' matrix. W is a dictionary with entries: - W['dnl']: positive vector - W['dnli']: componentwise inverse of W['dnl'] - W['d']: positive vector - W['di']: componentwise inverse of W['d'] - W['v']: lists of 2nd order cone vectors with unit hyperbolic norms - W['beta']: list of positive numbers - W['r']: list of square matrices - W['rti']: list of square matrices. rti[k] is the inverse transpose of r[k]. The 'dnl' and 'dnli' entries are optional, and only present when the function is called from the nonlinear solver. """ from cvxopt import blas ind = 0 # Scaling for nonlinear component xk is xk := dnl .* xk; inverse # scaling is xk ./ dnl = dnli .* xk, where dnl = W['dnl'], # dnli = W['dnli']. if 'dnl' in W: if inverse == 'N': w = W['dnl'] else: w = W['dnli'] for k in range(x.size[1]): blas.tbmv(w, x, n=w.size[0], k=0, ldA=1, offsetx=k * x.size[0]) ind += w.size[0] # Scaling for linear 'l' component xk is xk := d .* xk; inverse # scaling is xk ./ d = di .* xk, where d = W['d'], di = W['di']. if inverse == 'N': w = W['d'] else: w = W['di'] for k in range(x.size[1]): blas.tbmv(w, x, n=w.size[0], k=0, ldA=1, offsetx=k * x.size[0] + ind) ind += w.size[0] # Scaling for 'q' component is # # xk := beta * (2*v*v' - J) * xk # = beta * (2*v*(xk'*v)' - J*xk) # # where beta = W['beta'][k], v = W['v'][k], J = [1, 0; 0, -I]. # # Inverse scaling is # # xk := 1/beta * (2*J*v*v'*J - J) * xk # = 1/beta * (-J) * (2*v*((-J*xk)'*v)' + xk). w = matrix(0.0, (x.size[1], 1)) for k in range(len(W['v'])): v = W['v'][k] m = v.size[0] if inverse == 'I': blas.scal(-1.0, x, offset=ind, inc=x.size[0]) blas.gemv(x, v, w, trans='T', m=m, n=x.size[1], offsetA=ind, ldA=x.size[0]) blas.scal(-1.0, x, offset=ind, inc=x.size[0]) blas.ger(v, w, x, alpha=2.0, m=m, n=x.size[1], ldA=x.size[0], offsetA=ind) if inverse == 'I': blas.scal(-1.0, x, offset=ind, inc=x.size[0]) a = 1.0 / W['beta'][k] else: a = W['beta'][k] for i in range(x.size[1]): blas.scal(a, x, n=m, offset=ind + i * x.size[0]) ind += m # Scaling for 's' component xk is # # xk := vec( r' * mat(xk) * r ) if trans = 'N' # xk := vec( r * mat(xk) * r' ) if trans = 'T'. # # r is kth element of W['r']. # # Inverse scaling is # # xk := vec( rti * mat(xk) * rti' ) if trans = 'N' # xk := vec( rti' * mat(xk) * rti ) if trans = 'T'. # # rti is kth element of W['rti']. maxn = max([0] + [r.size[0] for r in W['r']]) a = matrix(0.0, (maxn, maxn)) for k in range(len(W['r'])): if inverse == 'N': r = W['r'][k] if trans == 'N': t = 'T' else: t = 'N' else: r = W['rti'][k] t = trans n = r.size[0] for i in range(x.size[1]): # scale diagonal of xk by 0.5 blas.scal(0.5, x, offset=ind + i * x.size[0], inc=n + 1, n=n) # a = r*tril(x) (t is 'N') or a = tril(x)*r (t is 'T') blas.copy(r, a) if t == 'N': blas.trmm(x, a, side='R', m=n, n=n, ldA=n, ldB=n, offsetA=ind + i * x.size[0]) else: blas.trmm(x, a, side='L', m=n, n=n, ldA=n, ldB=n, offsetA=ind + i * x.size[0]) # x := (r*a' + a*r') if t is 'N' # x := (r'*a + a'*r) if t is 'T' blas.syr2k(r, a, x, trans=t, n=n, k=n, ldB=n, ldC=n, offsetC=ind + i * x.size[0]) ind += n ** 2