def einsum(subscripts, *operands):
return Matrix(xp.einsum(subscripts, *[o.array for o in operands]))
def optimize_cv(self, lr_group, direction, isite, num, percent=0):
if self.spectratype == "abs":
# quantum number restriction, |1><0|
up_exciton, down_exciton = 1, 0
elif self.spectratype == "emi":
# quantum number restriction, |0><1|
up_exciton, down_exciton = 0, 1
nexciton = 1
first_LR, second_LR, third_LR, forth_LR = lr_group
if self.method == "1site":
add_list = [isite - 1]
first_L = asxp(first_LR[isite - 1])
first_R = asxp(first_LR[isite])
second_L = asxp(second_LR[isite - 1])
second_R = asxp(second_LR[isite])
third_L = asxp(third_LR[isite - 1])
third_R = asxp(third_LR[isite])
forth_L = asxp(forth_LR[isite - 1])
forth_R = asxp(forth_LR[isite])
else:
add_list = [isite - 2, isite - 1]
first_L = asxp(first_LR[isite - 2])
first_R = asxp(first_LR[isite])
second_L = asxp(second_LR[isite - 2])
second_R = asxp(second_LR[isite])
third_L = asxp(third_LR[isite - 2])
third_R = asxp(third_LR[isite])
forth_L = asxp(forth_LR[isite - 2])
forth_R = asxp(forth_LR[isite])
xqnmat, xqnbigl, xqnbigr, xshape = \
self.construct_X_qnmat(add_list, direction)
dag_qnmat, dag_qnbigl, dag_qnbigr = self.swap(xqnmat, xqnbigl, xqnbigr,
direction)
nonzeros = np.sum(self.condition(dag_qnmat,
[down_exciton, up_exciton]))
if self.method == "1site":
guess = moveaxis(self.cv_mpo[isite - 1], (1, 2), (2, 1))
else:
guess = tensordot(moveaxis(self.cv_mpo[isite - 2], (1, 2), (2, 1)),
moveaxis(self.cv_mpo[isite - 1]),
axes=(-1, 0))
guess = guess[self.condition(dag_qnmat,
[down_exciton, up_exciton])].reshape(
nonzeros, 1)
if self.method == "1site":
# define dot path
path_1 = [([0, 1], "abc, adef -> bcdef"),
([2, 0], "bcdef, begh -> cdfgh"),
([1, 0], "cdfgh, fhi -> cdgi")]
path_2 = [([0, 1], "abcd, aefg -> bcdefg"),
([3, 0], "bcdefg, bfhi -> cdeghi"),
([2, 0], "cdeghi, djek -> cghijk"),
([1, 0], "cghijk, gilk -> chjl")]
path_4 = [([0, 1], "ab, acde -> bcde"), ([1,
0], "bcde, ef -> bcdf")]
vecb = multi_tensor_contract(
path_4, forth_L,
moveaxis(self.a_ket_mpo[isite - 1], (1, 2), (2, 1)), forth_R)
vecb = -self.eta * vecb
a_oper_isite = asxp(self.a_oper[isite - 1])
b_oper_isite = asxp(self.b_oper[isite - 1])
h_mpo_isite = asxp(self.h_mpo[isite - 1])
# construct preconditioner
Idt = xp.identity(h_mpo_isite.shape[1])
M1_1 = xp.einsum('aea->ae', first_L)
M1_2 = xp.einsum('eccf->ecf', a_oper_isite)
M1_3 = xp.einsum('dfd->df', first_R)
M1_4 = xp.einsum('bb->b', Idt)
path_m1 = [([0, 1], "ae,b->aeb"), ([2, 0], "aeb,ecf->abcf"),
([1, 0], "abcf, df->abcd")]
pre_M1 = multi_tensor_contract(path_m1, M1_1, M1_4, M1_2, M1_3)
pre_M1 = pre_M1[self.condition(dag_qnmat, [down_exciton, up_exciton])]
M2_1 = xp.einsum('aeag->aeg', second_L)
M2_2 = xp.einsum('eccf->ecf', b_oper_isite)
M2_3 = xp.einsum('gbbh->gbh', h_mpo_isite)
M2_4 = xp.einsum('dfdh->dfh', second_R)
path_m2 = [([0, 1], "aeg,gbh->aebh"), ([2, 0], "aebh,ecf->abchf"),
([1, 0], "abhcf,dfh->abcd")]
pre_M2 = multi_tensor_contract(path_m2, M2_1, M2_3, M2_2, M2_4)
pre_M2 = pre_M2[self.condition(dag_qnmat, [down_exciton, up_exciton])]
M4_1 = xp.einsum('faah->fah', third_L)
M4_4 = xp.einsum('gddi->gdi', third_R)
M4_5 = xp.einsum('cc->c', Idt)
M4_path = [([0, 1], "fah,febg->ahebg"), ([2, 0], "ahebg,hjei->abgji"),
([1, 0], "abgji,gdi->abjd")]
pre_M4 = multi_tensor_contract(M4_path, M4_1, h_mpo_isite, h_mpo_isite,
M4_4)
pre_M4 = xp.einsum('abbd->abd', pre_M4)
pre_M4 = xp.tensordot(pre_M4, M4_5, axes=0)
pre_M4 = xp.moveaxis(pre_M4, [2, 3], [3, 2])[self.condition(
dag_qnmat, [down_exciton, up_exciton])]
pre_M = (pre_M1 + 2 * pre_M2 + pre_M4)
indices = np.array(range(nonzeros))
indptr = np.array(range(nonzeros + 1))
pre_M = scipy.sparse.csc_matrix((asnumpy(pre_M), indices, indptr),
shape=(nonzeros, nonzeros))
M_x = lambda x: scipy.sparse.linalg.spsolve(pre_M, x)
M = scipy.sparse.linalg.LinearOperator((nonzeros, nonzeros), M_x)
count = 0
def hop(x):
nonlocal count
count += 1
dag_struct = asxp(self.dag2mat(xshape, x, dag_qnmat, direction))
if self.method == "1site":
M1 = multi_tensor_contract(path_1, first_L, dag_struct,
a_oper_isite, first_R)
M2 = multi_tensor_contract(path_2, second_L, dag_struct,
b_oper_isite, h_mpo_isite, second_R)
M2 = xp.moveaxis(M2, (1, 2), (2, 1))
M3 = multi_tensor_contract(path_2, third_L, h_mpo_isite,
dag_struct, h_mpo_isite, third_R)
M3 = xp.moveaxis(M3, (1, 2), (2, 1))
cout = M1 + 2 * M2 + M3
cout = cout[self.condition(dag_qnmat,
[down_exciton, up_exciton])].reshape(
nonzeros, 1)
return asnumpy(cout)
# Matrix A and Vector b
vecb = asnumpy(vecb)[self.condition(
dag_qnmat, [down_exciton, up_exciton])].reshape(nonzeros, 1)
mata = scipy.sparse.linalg.LinearOperator((nonzeros, nonzeros),
matvec=hop)
# conjugate gradient method
# x, info = scipy.sparse.linalg.cg(MatA, VecB, atol=0)
if num == 1:
x, info = scipy.sparse.linalg.cg(mata,
vecb,
tol=1.e-5,
maxiter=500,
M=M,
atol=0)
else:
x, info = scipy.sparse.linalg.cg(mata,
vecb,
tol=1.e-5,
x0=guess,
maxiter=500,
M=M,
atol=0)
# logger.info(f"linear eq dim: {nonzeros}")
# logger.info(f'times for hop:{count}')
self.hop_time.append(count)
if info != 0:
logger.warning(
f"cg not converged, vecb.norm:{np.linalg.norm(vecb)}")
l_value = np.inner(
hop(x).reshape(1, nonzeros), x.reshape(1, nonzeros)) - \
2 * np.inner(vecb.reshape(1, nonzeros), x.reshape(1, nonzeros))
x = self.dag2mat(xshape, x, dag_qnmat, direction)
if self.method == "1site":
x = np.moveaxis(x, [1, 2], [2, 1])
x, xdim, xqn, compx = self.x_svd(x,
xqnbigl,
xqnbigr,
nexciton,
direction,
percent=percent)
if self.method == "1site":
self.cv_mpo[isite - 1] = x
if direction == "left":
if isite != 1:
self.cv_mpo[isite - 2] = \
tensordot(self.cv_mpo[isite - 2], compx, axes=(-1, 0))
self.cv_mpo.qn[isite - 1] = xqn
else:
self.cv_mpo[isite - 1] = \
tensordot(compx, self.cv_mpo[isite - 1], axes=(-1, 0))
elif direction == "right":
if isite != len(self.cv_mpo):
self.cv_mpo[isite] = \
tensordot(compx, self.cv_mpo[isite], axes=(-1, 0))
self.cv_mpo.qn[isite] = xqn
else:
self.cv_mpo[isite - 1] = \
tensordot(self.cv_mpo[isite - 1], compx, axes=(-1, 0))
else:
if direction == "left":
self.cv_mpo[isite - 2] = compx
self.cv_mpo[isite - 1] = x
else:
self.cv_mpo[isite - 2] = x
self.cv_mpo[isite - 1] = compx
self.cv_mpo.qn[isite - 1] = xqn
return l_value[0][0]
def optimize_cv(self, lr_group, direction, isite, num, percent=0.0):
# depending on the spectratype, to restrict the exction
first_LR = lr_group[0]
second_LR = lr_group[1]
if self.spectratype == "abs":
constrain_qn = 1
else:
constrain_qn = 0
# this function aims at solving the work equation of ZT CV-DMRG
# L = <CV|op_a|CV>+2\eta<op_b|CV>, take a derivative to local CV
# S-a-S-e-S S-a-S-d-S
# | d | | | |
# O-b-O-g-O * CV[isite-1] = -\eta | c |
# | f | | | |
# S-c- -h-S S-b- -e-S
# note to be a_mat * x = vec_b
# the environment matrix
if self.method == "1site":
addlist = [isite - 1]
first_L = asxp(first_LR[isite - 1])
first_R = asxp(first_LR[isite])
second_L = asxp(second_LR[isite - 1])
second_R = asxp(second_LR[isite])
else:
addlist = [isite - 2, isite - 1]
first_L = asxp(first_LR[isite - 2])
first_R = asxp(first_LR[isite])
second_L = asxp(second_LR[isite - 2])
second_R = asxp(second_LR[isite])
if direction == 'left':
system = 'R'
else:
system = 'L'
# this part just be similar with ground state calculation
qnmat, qnbigl, qnbigr = svd_qn.construct_qnmat(
self.cv_mps, self.mpo.pbond_list,
addlist, self.method, system)
xshape = qnmat.shape
nonzeros = np.sum(qnmat == constrain_qn)
if self.method == '1site':
guess = self.cv_mps[isite - 1][qnmat == constrain_qn].reshape(nonzeros, 1)
path_b = [([0, 1], "ab, acd->bcd"),
([1, 0], "bcd, de->bce")]
vec_b = multi_tensor_contract(
path_b, second_L, self.b_oper[isite - 1], second_R
)[qnmat == constrain_qn].reshape(nonzeros, 1)
else:
guess = tensordot(
self.cv_mps[isite - 2], self.cv_mps[isite - 1], axes=(-1, 0)
)
guess = guess[qnmat == constrain_qn].reshape(nonzeros, 1)
path_b = [([0, 1], "ab, acd->bcd"),
([2, 0], "bcd, def->bcef"),
([1, 0], "bcef, fg->bceg")]
vec_b = multi_tensor_contract(
path_b, second_L, self.b_oper[isite - 2],
self.b_oper[isite - 1], second_R
)[qnmat == constrain_qn].reshape(nonzeros, 1)
if self.method == "2site":
a_oper_isite2 = asxp(self.a_oper[isite - 2])
else:
a_oper_isite2 = None
a_oper_isite1 = asxp(self.a_oper[isite - 1])
# use the diagonal part of mat_a to construct the preconditinoner for linear solver
if self.method == "1site":
part_l = xp.einsum('abca->abc', first_L)
part_r = xp.einsum('hfgh->hfg', first_R)
path_pre = [([0, 1], "abc, bdef->acdef"),
([1, 0], "acdef, hfg->acdehg")]
pre_a_mat1 = multi_tensor_contract(path_pre, part_l, a_oper_isite1,
part_r)
path_pre2 = [([0, 1], "acdehg, ceig->adhi")]
pre_a_mat1 = multi_tensor_contract(path_pre2, pre_a_mat1, a_oper_isite1)
pre_a_mat1 = xp.einsum('adhd->adh', pre_a_mat1)[qnmat == constrain_qn]
# pre_a_mat1 = xp.einsum('abca, bdef, cedg, hfgh->adh', first_L, a_oper_isite1,
# a_oper_isite1, first_R)[qnmat == constrain_qn]
cv_shape = self.cv_mps[isite - 1].shape
pre_a_mat2 = xp.ones(cv_shape)[qnmat == constrain_qn]
pre_a_mat = pre_a_mat1 + pre_a_mat2 * self.eta**2
else:
pre_a_mat1 = xp.einsum(
'abca, bdef, cedg, fhij, gihk, ljkl->adhl', first_L, a_oper_isite2, a_oper_isite2,
a_oper_isite1, a_oper_isite1, first_R)[qnmat == constrain_qn]
cv_shape1 = self.cv_mps[isite - 2].shape
cv_shape2 = self.cv_mps[isite - 1].shape
new_shape = [cv_shape1[0], cv_shape1[1], cv_shape2[1], cv_shape2[2]]
pre_a_mat2 = xp.ones(new_shape)[qnmat == constrain_qn]
pre_a_mat = pre_a_mat1 + pre_a_mat2 * self.eta**2
pre_a_mat = np.diag(1./asnumpy(pre_a_mat))
count = 0
def hop(c):
nonlocal count
count += 1
xstruct = asxp(svd_qn.cvec2cmat(xshape, c, qnmat, constrain_qn))
if self.method == "1site":
path_a = [([0, 1], "abcd, aef->bcdef"),
([3, 0], "bcdef, begh->cdfgh"),
([2, 0], "cdfgh, cgij->dfhij"),
([1, 0], "dfhij, fhjk->dik")]
ax1 = multi_tensor_contract(path_a, first_L, xstruct,
a_oper_isite1, a_oper_isite1, first_R)
ax2 = xstruct
ax = ax1 + ax2 * self.eta**2
else:
path_a = [([0, 1], "abcd, aefg->bcdefg"),
([5, 0], "bcdefg, behi->cdfghi"),
([4, 0], "cdfghi, ifjk->cdghjk"),
([3, 0], "cdghjk, chlm->dgjklm"),
([2, 0], "dgjklm, mjno->dgklno"),
([1, 0], "dgklno, gkop->dlnp")]
ax1 = multi_tensor_contract(path_a, first_L, xstruct,
a_oper_isite2, a_oper_isite1,
a_oper_isite2, a_oper_isite1,
first_R)
ax2 = xstruct
ax = ax1 + ax2 * self.eta**2
cout = ax[qnmat == constrain_qn].reshape(nonzeros, 1)
return asnumpy(cout)
mat_a = scipy.sparse.linalg.LinearOperator((nonzeros, nonzeros), matvec=hop)
# for the first two sweep, not use the previous matrix as initial guess
# at the inital stage, they are far from from the optimized one
if num in [1, 2]:
x, info = scipy.sparse.linalg.cg(mat_a, asnumpy(vec_b), atol=0)
else:
x, info = scipy.sparse.linalg.cg(mat_a, asnumpy(vec_b), tol=1.e-5,
x0=guess, M=pre_a_mat, atol=0)
# logger.info(f'hop times:{count}')
self.hop_time.append(count)
if info != 0:
logger.info(f"iteration solver not converged")
# the value of the functional L
l_value = np.inner(hop(x).reshape(1, nonzeros), x.reshape(1, nonzeros)
) - 2 * np.inner(
asnumpy(vec_b).reshape(1, nonzeros), x.reshape(1, nonzeros))
xstruct = svd_qn.cvec2cmat(xshape, x, qnmat, constrain_qn)
x, xdim, xqn, compx = \
solver.renormalization_svd(xstruct, qnbigl, qnbigr, system,
constrain_qn, self.m_max, percent)
if self.method == "1site":
self.cv_mps[isite - 1] = x
if direction == "left":
if isite != 1:
self.cv_mps[isite - 2] = tensordot(
self.cv_mps[isite - 2], compx, axes=(-1, 0))
self.cv_mps.qn[isite - 1] = xqn
else:
self.cv_mps[isite - 1] = tensordot(
compx, self.cv_mps[isite - 1], axes=(-1, 0))
self.cv_mps.qn[isite - 1] = [0]
elif direction == "right":
if isite != len(self.cv_mps):
self.cv_mps[isite] = tensordot(
compx, self.cv_mps[isite], axes=(-1, 0))
self.cv_mps.qn[isite] = xqn
else:
self.cv_mps[isite - 1] = tensordot(
self.cv_mps[isite - 1], compx, axes=(-1, 0))
self.cv_mps.qn[isite] = [0]
else:
if direction == "left":
self.cv_mps[isite - 1] = x
self.cv_mps[isite - 2] = compx
else:
self.cv_mps[isite - 2] = x
self.cv_mps[isite - 1] = compx
self.cv_mps.qn[isite - 1] = xqn
return l_value[0][0]
def optimize_cv(self, lr_group, isite, percent=0.0):
# depending on the spectratype, to restrict the exction
first_LR = lr_group[0]
second_LR = lr_group[1]
constrain_qn = self.cv_mps.qntot
# this function aims at solving the work equation of ZT CV-DMRG
# L = <CV|op_a|CV>+2\eta<op_b|CV>, take a derivative to local CV
# S-a-S-e-S S-a-S-d-S
# | d | | | |
# O-b-O-g-O * CV[isite-1] = -\eta | c |
# | f | | | |
# S-c- -h-S S-b- -e-S
# note to be a_mat * x = vec_b
# the environment matrix
if self.method == "1site":
cidx = [isite - 1]
first_L = asxp(first_LR[isite - 1])
first_R = asxp(first_LR[isite])
second_L = asxp(second_LR[isite - 1])
second_R = asxp(second_LR[isite])
else:
cidx = [isite - 2, isite - 1]
first_L = asxp(first_LR[isite - 2])
first_R = asxp(first_LR[isite])
second_L = asxp(second_LR[isite - 2])
second_R = asxp(second_LR[isite])
# this part just be similar with ground state calculation
qnbigl, qnbigr, qnmat = self.cv_mps._get_big_qn(cidx)
xshape = qnmat.shape
nonzeros = int(np.sum(qnmat == constrain_qn))
if self.method == '1site':
guess = self.cv_mps[isite - 1][qnmat == constrain_qn]
path_b = [([0, 1], "ab, acd->bcd"),
([1, 0], "bcd, de->bce")]
vec_b = multi_tensor_contract(
path_b, second_L, self.b_mps[isite - 1], second_R
)[qnmat == constrain_qn]
else:
guess = tensordot(
self.cv_mps[isite - 2], self.cv_mps[isite - 1], axes=(-1, 0)
)[qnmat == constrain_qn]
path_b = [([0, 1], "ab, acd->bcd"),
([2, 0], "bcd, def->bcef"),
([1, 0], "bcef, fg->bceg")]
vec_b = multi_tensor_contract(
path_b, second_L, self.b_mps[isite - 2],
self.b_mps[isite - 1], second_R
)[qnmat == constrain_qn]
if self.method == "2site":
a_oper_isite2 = asxp(self.a_oper[isite - 2])
else:
a_oper_isite2 = None
a_oper_isite1 = asxp(self.a_oper[isite - 1])
# use the diagonal part of mat_a to construct the preconditinoner
# for linear solver
part_l = xp.einsum('abca->abc', first_L)
part_r = xp.einsum('hfgh->hfg', first_R)
if self.method == "1site":
# S-a d h-S
# O-b -O- f-O
# | e |
# O-c -O- g-O
# S-a i h-S
path_pre = [([0, 1], "abc, bdef -> acdef"),
([1, 0], "acdef, ceig -> adfig")]
a_diag = multi_tensor_contract(path_pre, part_l, a_oper_isite1,
a_oper_isite1)
a_diag = xp.einsum("adfdg -> adfg", a_diag)
a_diag = xp.tensordot(a_diag, part_r,
axes=([2, 3], [1, 2]))[qnmat == constrain_qn]
else:
# S-a d k h-S
# O-b -O- j -O- f-O
# | e l |
# O-c -O- m -O- g-O
# S-a i n h-S
# first left half, second right half, last contraction
path_pre = [([0, 1], "abc, bdej -> acdej"),
([1, 0], "acdej, ceim -> adjim")]
a_diagl = multi_tensor_contract(path_pre, part_l, a_oper_isite2,
a_oper_isite2)
a_diagl = xp.einsum("adjdm -> adjm", a_diagl)
path_pre = [([0, 1], "hfg, jklf -> hgjkl"),
([1, 0], "hgjkl, mlng -> hjkmn")]
a_diagr = multi_tensor_contract(path_pre, part_r, a_oper_isite1,
a_oper_isite1)
a_diagr = xp.einsum("hjkmk -> khjm", a_diagr)
a_diag = xp.tensordot(
a_diagl, a_diagr, axes=([2, 3], [2, 3]))[qnmat == constrain_qn]
a_diag = asnumpy(a_diag + xp.ones(nonzeros) * self.eta**2)
M_x = lambda x: x / a_diag
pre_M = scipy.sparse.linalg.LinearOperator((nonzeros, nonzeros), M_x)
count = 0
# cache oe path
if self.method == "2site":
expr = oe.contract_expression(
"abcd, befh, cfgi, hjkn, iklo, mnop, dglp -> aejm",
first_L, a_oper_isite2, a_oper_isite2, a_oper_isite1,
a_oper_isite1, first_R, xshape,
constants=[0, 1, 2, 3, 4, 5])
def hop(c):
nonlocal count
count += 1
xstruct = asxp(cvec2cmat(xshape, c, qnmat, constrain_qn))
if self.method == "1site":
path_a = [([0, 1], "abcd, aef->bcdef"),
([3, 0], "bcdef, begh->cdfgh"),
([2, 0], "cdfgh, cgij->dfhij"),
([1, 0], "dfhij, fhjk->dik")]
ax1 = multi_tensor_contract(path_a, first_L, xstruct,
a_oper_isite1, a_oper_isite1, first_R)
else:
# opt_einsum v3.2.1 is not bad, ~10% faster than the hand-design
# contraction path for this complicated cases and consumes a little bit less memory
# this is the only place in renormalizer we use opt_einsum now.
# we keep it here just for a demo.
# ax1 = oe.contract("abcd, befh, cfgi, hjkn, iklo, mnop, dglp -> aejm",
# first_L, a_oper_isite2, a_oper_isite2, a_oper_isite1,
# a_oper_isite1, first_R, xstruct)
if USE_GPU:
oe_backend = "cupy"
else:
oe_backend = "numpy"
ax1 = expr(xstruct, backend=oe_backend)
#print(oe.contract_path("abcd, befh, cfgi, hjkn, iklo, mnop, dglp -> aejm",
# first_L, a_oper_isite2, a_oper_isite2, a_oper_isite1,
# a_oper_isite1, first_R, xstruct))
#path_a = [([0, 1], "abcd, aefg->bcdefg"),
# ([5, 0], "bcdefg, behi->cdfghi"),
# ([4, 0], "cdfghi, ifjk->cdghjk"),
# ([3, 0], "cdghjk, chlm->dgjklm"),
# ([2, 0], "dgjklm, mjno->dgklno"),
# ([1, 0], "dgklno, gkop->dlnp")]
#ax1 = multi_tensor_contract(path_a, first_L, xstruct,
# a_oper_isite2, a_oper_isite1,
# a_oper_isite2, a_oper_isite1,
# first_R)
ax = ax1 + xstruct * self.eta**2
cout = ax[qnmat == constrain_qn]
return asnumpy(cout)
mat_a = scipy.sparse.linalg.LinearOperator((nonzeros, nonzeros),
matvec=hop)
x, info = scipy.sparse.linalg.cg(mat_a, asnumpy(vec_b), tol=1.e-5,
x0=asnumpy(guess),
M=pre_M, atol=0)
self.hop_time.append(count)
if info != 0:
logger.info(f"iteration solver not converged")
# the value of the functional L
l_value = xp.dot(asxp(hop(x)), asxp(x)) - 2 * xp.dot(vec_b, asxp(x))
xstruct = cvec2cmat(xshape, x, qnmat, constrain_qn)
self.cv_mps._update_mps(xstruct, cidx, qnbigl, qnbigr, self.m_max, percent)
return float(l_value)
def kernel(self, restart=False, include_psi0=False):
r"""calculate the roots
Parameters
----------
restart: bool, optional
if restart from the former converged root. Default is ``False``.
If ``restart = True``, ``include_psi0`` must be the same as the
former calculation.
include_psi0: bool, optional
if the basis of Hamiltonian includes the ground state
:math:`\Psi_0`. Default is ``False``.
Returns
-------
e: np.ndarray
the energy of the states, if ``include_psi0 = True``, the first
element is the ground state energy, otherwise, it is the energy of
the first excited state.
"""
# right canonical mps
mpo = self.hmpo
nroots = self.nroots
algo = self.algo
site_num = mpo.site_num
if not restart:
# make sure that M is not redundant near the edge
mps = self.mps.ensure_right_canon().canonicalise().normalize().canonicalise()
logger.debug(f"reference mps shape, {mps}")
mps_r_cano = mps.copy()
assert mps.to_right
tangent_u = []
for ims, ms in enumerate(mps):
shape = list(ms.shape)
u, s, vt = scipy.linalg.svd(ms.l_combine(), full_matrices=True)
rank = len(s)
if include_psi0 and ims == site_num-1:
tangent_u.append(u.reshape(shape[:-1]+[-1]))
else:
if rank < u.shape[1]:
tangent_u.append(u[:,rank:].reshape(shape[:-1]+[-1]))
else:
tangent_u.append(None) # the tangent space is None
mps[ims] = u[:,:rank].reshape(shape[:-1]+[-1])
vt = xp.einsum("i, ij -> ij", asxp(s), asxp(vt))
if ims == site_num-1:
assert vt.size == 1 and xp.allclose(vt, 1)
else:
mps[ims+1] = asnumpy(tensordot(vt, mps[ims+1], ([-1],[0])))
mps_l_cano = mps.copy()
mps_l_cano.to_right = False
mps_l_cano.qnidx = site_num-1
else:
mps_l_cano, mps_r_cano, tangent_u, tda_coeff_list = self.wfn
cguess = []
for iroot in range(len(tda_coeff_list)):
tda_coeff = tda_coeff_list[iroot]
x = [c.flatten() for c in tda_coeff if c is not None]
x = np.concatenate(x,axis=None)
cguess.append(x)
cguess = np.stack(cguess, axis=1)
xshape = []
xsize = 0
for ims in range(site_num):
if tangent_u[ims] is None:
xshape.append((0,0))
else:
if ims == site_num-1:
xshape.append((tangent_u[ims].shape[-1], 1))
else:
xshape.append((tangent_u[ims].shape[-1], mps_r_cano[ims+1].shape[0]))
xsize += np.prod(xshape[-1])
logger.debug(f"DMRG-TDA H dimension: {xsize}")
if USE_GPU:
oe_backend = "cupy"
else:
oe_backend = "numpy"
mps_tangent = mps_r_cano.copy()
environ = Environ(mps_tangent, mpo, "R")
hdiag = []
for ims in range(site_num):
ltensor = environ.GetLR(
"L", ims-1, mps_tangent, mpo, itensor=None,
method="System"
)
rtensor = environ.GetLR(
"R", ims+1, mps_tangent, mpo, itensor=None,
method="Enviro"
)
if tangent_u[ims] is not None:
u = asxp(tangent_u[ims])
tmp = oe.contract("abc, ded, bghe, agl, chl -> ld", ltensor, rtensor,
asxp(mpo[ims]), u, u, backend=oe_backend)
hdiag.append(asnumpy(tmp))
mps_tangent[ims] = mps_l_cano[ims]
hdiag = np.concatenate(hdiag, axis=None)
count = 0
# recover the vector-like x back to the ndarray tda_coeff
def reshape_x(x):
tda_coeff = []
offset = 0
for shape in xshape:
if shape == (0,0):
tda_coeff.append(None)
else:
size = np.prod(shape)
tda_coeff.append(x[offset:size+offset].reshape(shape))
offset += size
assert offset == xsize
return tda_coeff
def hop(x):
# H*X
nonlocal count
count += 1
assert len(x) == xsize
tda_coeff = reshape_x(x)
res = [np.zeros_like(coeff) if coeff is not None else None for coeff in tda_coeff]
# fix ket and sweep bra and accumulate into res
for ims in range(site_num):
if tda_coeff[ims] is None:
assert tangent_u[ims] is None
continue
# mix-canonical mps
mps_tangent = merge(mps_l_cano, mps_r_cano, ims+1)
mps_tangent[ims] = tensordot(tangent_u[ims], tda_coeff[ims], (-1, 0))
mps_tangent_conj = mps_r_cano.copy()
environ = Environ(mps_tangent, mpo, "R", mps_conj=mps_tangent_conj)
for ims_conj in range(site_num):
ltensor = environ.GetLR(
"L", ims_conj-1, mps_tangent, mpo, itensor=None,
mps_conj=mps_tangent_conj,
method="System"
)
rtensor = environ.GetLR(
"R", ims_conj+1, mps_tangent, mpo, itensor=None,
mps_conj=mps_tangent_conj,
method="Enviro"
)
if tda_coeff[ims_conj] is not None:
# S-a l-S
# d
# O-b-O-f-O
# e
# S-c k-S
path = [
([0, 1], "abc, cek -> abek"),
([2, 0], "abek, bdef -> akdf"),
([1, 0], "akdf, lfk -> adl"),
]
out = multi_tensor_contract(
path, ltensor, asxp(mps_tangent[ims_conj]),
asxp(mpo[ims_conj]), rtensor
)
res[ims_conj] += asnumpy(tensordot(tangent_u[ims_conj], out,
([0,1], [0,1])))
# mps_conj combine
mps_tangent_conj[ims_conj] = mps_l_cano[ims_conj]
res = [mat for mat in res if mat is not None]
return np.concatenate(res, axis=None)
if algo == "davidson":
if restart:
cguess = [cguess[:,i] for i in range(cguess.shape[1])]
else:
cguess = [np.random.random(xsize) - 0.5]
precond = lambda x, e, *args: x / (hdiag - e + 1e-4)
e, c = davidson(
hop, cguess, precond, max_cycle=100,
nroots=nroots, max_memory=64000
)
if nroots == 1:
c = [c]
c = np.stack(c, axis=1)
elif algo == "primme":
if not restart:
cguess = None
def multi_hop(x):
if x.ndim == 1:
return hop(x)
elif x.ndim == 2:
return np.stack([hop(x[:,i]) for i in range(x.shape[1])],axis=1)
else:
assert False
def precond(x):
if x.ndim == 1:
return np.einsum("i, i -> i", 1/(hdiag+1e-4), x)
elif x.ndim ==2:
return np.einsum("i, ij -> ij", 1/(hdiag+1e-4), x)
else:
assert False
A = scipy.sparse.linalg.LinearOperator((xsize,xsize),
matvec=multi_hop, matmat=multi_hop)
M = scipy.sparse.linalg.LinearOperator((xsize,xsize),
matvec=precond, matmat=precond)
e, c = primme.eigsh(A, k=min(nroots,xsize), which="SA",
v0=cguess,
OPinv=M,
method="PRIMME_DYNAMIC",
tol=1e-6)
else:
assert False
logger.debug(f"H*C times: {count}")
tda_coeff_list = []
for iroot in range(nroots):
tda_coeff_list.append(reshape_x(c[:,iroot]))
self.e = np.array(e)
self.wfn = [mps_l_cano, mps_r_cano, tangent_u, tda_coeff_list]
return self.e
def optimize_cv(self, lr_group, isite, percent=0):
if self.spectratype == "abs":
# quantum number restriction, |1><0|
up_exciton, down_exciton = 1, 0
elif self.spectratype == "emi":
# quantum number restriction, |0><1|
up_exciton, down_exciton = 0, 1
nexciton = 1
first_LR, second_LR, third_LR, forth_LR = lr_group
if self.method == "1site":
add_list = [isite - 1]
first_L = asxp(first_LR[isite - 1])
first_R = asxp(first_LR[isite])
second_L = asxp(second_LR[isite - 1])
second_R = asxp(second_LR[isite])
third_L = asxp(third_LR[isite - 1])
third_R = asxp(third_LR[isite])
forth_L = asxp(forth_LR[isite - 1])
forth_R = asxp(forth_LR[isite])
else:
add_list = [isite - 2, isite - 1]
first_L = asxp(first_LR[isite - 2])
first_R = asxp(first_LR[isite])
second_L = asxp(second_LR[isite - 2])
second_R = asxp(second_LR[isite])
third_L = asxp(third_LR[isite - 2])
third_R = asxp(third_LR[isite])
forth_L = asxp(forth_LR[isite - 2])
forth_R = asxp(forth_LR[isite])
xqnmat, xqnbigl, xqnbigr, xshape = \
self.construct_X_qnmat(add_list)
dag_qnmat, dag_qnbigl, dag_qnbigr = self.swap(xqnmat, xqnbigl, xqnbigr)
nonzeros = int(
np.sum(self.condition(dag_qnmat, [down_exciton, up_exciton])))
if self.method == "1site":
guess = moveaxis(self.cv_mpo[isite - 1], (1, 2), (2, 1))
else:
guess = tensordot(moveaxis(self.cv_mpo[isite - 2], (1, 2), (2, 1)),
moveaxis(self.cv_mpo[isite - 1]),
axes=(-1, 0))
guess = guess[self.condition(dag_qnmat, [down_exciton, up_exciton])]
if self.method == "1site":
# define dot path
path_1 = [([0, 1], "abcd, aefg -> bcdefg"),
([3, 0], "bcdefg, bfhi -> cdeghi"),
([2, 0], "cdeghi, chjk -> degijk"),
([1, 0], "degijk, gikl -> dejl")]
path_2 = [([0, 1], "abcd, aefg -> bcdefg"),
([3, 0], "bcdefg, bfhi -> cdeghi"),
([2, 0], "cdeghi, djek -> cghijk"),
([1, 0], "cghijk, gilk -> chjl")]
path_3 = [([0, 1], "ab, acde -> bcde"), ([1,
0], "bcde, ef -> bcdf")]
vecb = multi_tensor_contract(
path_3, forth_L, moveaxis(self.b_mpo[isite - 1], (1, 2),
(2, 1)),
forth_R)[self.condition(dag_qnmat, [down_exciton, up_exciton])]
a_oper_isite = asxp(self.a_oper[isite - 1])
h_mpo_isite = asxp(self.h_mpo[isite - 1])
# construct preconditioner
Idt = xp.identity(h_mpo_isite.shape[1])
M1_1 = xp.einsum('abca->abc', first_L)
path_m1 = [([0, 1], "abc, bdef->acdef"), ([1,
0], "acdef, cegh->adfgh")]
M1_2 = multi_tensor_contract(path_m1, M1_1, a_oper_isite, a_oper_isite)
M1_2 = xp.einsum("abcbd->abcd", M1_2)
M1_3 = xp.einsum('ecde->ecd', first_R)
M1_4 = xp.einsum('ff->f', Idt)
path_m1 = [([0, 1], "abcd,ecd->abe"), ([1, 0], "abe,f->abef")]
pre_M1 = multi_tensor_contract(path_m1, M1_2, M1_3, M1_4)
pre_M1 = xp.moveaxis(pre_M1, [-2, -1], [-1, -2])[self.condition(
dag_qnmat, [down_exciton, up_exciton])]
M2_1 = xp.einsum('aeag->aeg', second_L)
M2_2 = xp.einsum('eccf->ecf', a_oper_isite)
M2_3 = xp.einsum('gbbh->gbh', h_mpo_isite)
M2_4 = xp.einsum('dfdh->dfh', second_R)
path_m2 = [([0, 1], "aeg,gbh->aebh"), ([2, 0], "aebh,ecf->abchf"),
([1, 0], "abhcf,dfh->abcd")]
pre_M2 = multi_tensor_contract(path_m2, M2_1, M2_3, M2_2, M2_4)
pre_M2 = pre_M2[self.condition(dag_qnmat, [down_exciton, up_exciton])]
M4_1 = xp.einsum('faah->fah', third_L)
M4_4 = xp.einsum('gddi->gdi', third_R)
M4_5 = xp.einsum('cc->c', Idt)
M4_path = [([0, 1], "fah,febg->ahebg"), ([2, 0], "ahebg,hjei->abgji"),
([1, 0], "abgji,gdi->abjd")]
pre_M4 = multi_tensor_contract(M4_path, M4_1, h_mpo_isite, h_mpo_isite,
M4_4)
pre_M4 = xp.einsum('abbd->abd', pre_M4)
pre_M4 = xp.tensordot(pre_M4, M4_5, axes=0)
pre_M4 = xp.moveaxis(pre_M4, [2, 3], [3, 2])[self.condition(
dag_qnmat, [down_exciton, up_exciton])]
M_x = lambda x: asnumpy(
asxp(x) /
(pre_M1 + 2 * pre_M2 + pre_M4 + xp.ones(nonzeros) * self.eta**2))
pre_M = scipy.sparse.linalg.LinearOperator((nonzeros, nonzeros), M_x)
count = 0
def hop(x):
nonlocal count
count += 1
dag_struct = asxp(self.dag2mat(xshape, x, dag_qnmat))
if self.method == "1site":
M1 = multi_tensor_contract(path_1, first_L, dag_struct,
a_oper_isite, a_oper_isite, first_R)
M2 = multi_tensor_contract(path_2, second_L, dag_struct,
a_oper_isite, h_mpo_isite, second_R)
M2 = xp.moveaxis(M2, (1, 2), (2, 1))
M3 = multi_tensor_contract(path_2, third_L, h_mpo_isite,
dag_struct, h_mpo_isite, third_R)
M3 = xp.moveaxis(M3, (1, 2), (2, 1))
cout = M1 + 2 * M2 + M3 + dag_struct * self.eta**2
cout = cout[self.condition(dag_qnmat, [down_exciton, up_exciton])]
return asnumpy(cout)
# Matrix A
mat_a = scipy.sparse.linalg.LinearOperator((nonzeros, nonzeros),
matvec=hop)
x, info = scipy.sparse.linalg.cg(mat_a,
asnumpy(vecb),
tol=1.e-5,
x0=asnumpy(guess),
maxiter=500,
M=pre_M,
atol=0)
# logger.info(f"linear eq dim: {nonzeros}")
# logger.info(f'times for hop:{count}')
self.hop_time.append(count)
if info != 0:
logger.warning(
f"cg not converged, vecb.norm:{xp.linalg.norm(vecb)}")
l_value = xp.dot(asxp(hop(x)), asxp(x)) - 2 * xp.dot(vecb, asxp(x))
x = self.dag2mat(xshape, x, dag_qnmat)
if self.method == "1site":
x = np.moveaxis(x, [1, 2], [2, 1])
x, xdim, xqn, compx = self.x_svd(x,
xqnbigl,
xqnbigr,
nexciton,
percent=percent)
if self.method == "1site":
self.cv_mpo[isite - 1] = x
if not self.cv_mpo.to_right:
if isite != 1:
self.cv_mpo[isite - 2] = \
tensordot(self.cv_mpo[isite - 2], compx, axes=(-1, 0))
self.cv_mpo.qn[isite - 1] = xqn
self.cv_mpo.qnidx = isite - 2
else:
self.cv_mpo[isite - 1] = \
tensordot(compx, self.cv_mpo[isite - 1], axes=(-1, 0))
self.cv_mpo.qnidx = 0
else:
if isite != len(self.cv_mpo):
self.cv_mpo[isite] = \
tensordot(compx, self.cv_mpo[isite], axes=(-1, 0))
self.cv_mpo.qn[isite] = xqn
self.cv_mpo.qnidx = isite
else:
self.cv_mpo[isite - 1] = \
tensordot(self.cv_mpo[isite - 1], compx, axes=(-1, 0))
self.cv_mpo.qnidx = self.cv_mpo.site_num - 1
else:
if not self.cv_mpo.to_right:
self.cv_mpo[isite - 2] = compx
self.cv_mpo[isite - 1] = x
self.cv_mpo.qnidx = isite - 2
else:
self.cv_mpo[isite - 2] = x
self.cv_mpo[isite - 1] = compx
self.cv_mpo.qnidx = isite - 1
self.cv_mpo.qn[isite - 1] = xqn
return float(l_value)
def optimize_mps(mps: Mps, mpo: Mpo, omega: float = None) -> Tuple[List, Mps]:
r""" DMRG ground state algorithm and state-averaged excited states algorithm
Parameters
----------
mps : renormalizer.mps.Mps
initial guess of mps
mpo : renormalizer.mps.Mpo
mpo of Hamiltonian
omega: float, optional
target the eigenpair near omega with special variational function
:math:(\hat{H}-\omega)^2. Default is `None`.
Returns
-------
energy : list
list of energy of each marco sweep.
:math:`[e_0, e_0, \cdots, e_0]` if ``nroots=1``.
:math:`[[e_0, \cdots, e_n], \dots, [e_0, \cdots, e_n]]` if ``nroots=n``.
mps : renormalizer.mps.Mps
optimized ground state mps. The input mps is overwritten and could not
be used anymore.
See Also
--------
renormalizer.utils.configs.OptimizeConfig : The optimization configuration.
"""
algo = mps.optimize_config.algo
method = mps.optimize_config.method
procedure = mps.optimize_config.procedure
inverse = mps.optimize_config.inverse
nroots = mps.optimize_config.nroots
assert method in ["2site", "1site"]
logger.info(f"optimization method: {method}")
logger.info(f"e_rtol: {mps.optimize_config.e_rtol}")
logger.info(f"e_atol: {mps.optimize_config.e_atol}")
if USE_GPU:
oe_backend = "cupy"
else:
oe_backend = "numpy"
# ensure that mps is left or right-canonical
# TODO: start from a mix-canonical MPS
if mps.is_left_canon:
mps.ensure_right_canon()
env = "R"
else:
mps.ensure_left_canon()
env = "L"
# in state-averged calculation, contains C of each state for better initial
# guess
averaged_ms = None
# the index of active site of the returned mps
res_mps_idx = None
# target eigenstate close to omega with (H-omega)^2
# construct the environment matrix
if omega is not None:
identity = Mpo.identity(mpo.model)
mpo = mpo.add(identity.scale(-omega))
environ = Environ(mps, [mpo, mpo], env)
else:
environ = Environ(mps, mpo, env)
macro_iteration_result = []
converged = False
for isweep, (mmax, percent) in enumerate(procedure):
logger.debug(f"isweep: {isweep}")
logger.debug(f"mmax, percent: {mmax}, {percent}")
logger.debug(f"{mps}")
micro_iteration_result = []
for imps in mps.iter_idx_list(full=True):
if method == "2site" and \
((mps.to_right and imps == mps.site_num-1)
or ((not mps.to_right) and imps == 0)):
break
if mps.to_right:
lmethod, rmethod = "System", "Enviro"
else:
lmethod, rmethod = "Enviro", "System"
if method == "1site":
lidx = imps - 1
cidx = [imps]
ridx = imps + 1
elif method == "2site":
if mps.to_right:
lidx = imps - 1
cidx = [imps, imps + 1]
ridx = imps + 2
else:
lidx = imps - 2
cidx = [imps - 1, imps] # center site
ridx = imps + 1
else:
assert False
logger.debug(f"optimize site: {cidx}")
if omega is None:
operator = mpo
else:
operator = [mpo, mpo]
ltensor = environ.GetLR("L",
lidx,
mps,
operator,
itensor=None,
method=lmethod)
rtensor = environ.GetLR("R",
ridx,
mps,
operator,
itensor=None,
method=rmethod)
# get the quantum number pattern
qnbigl, qnbigr, qnmat = mps._get_big_qn(cidx)
cshape = qnmat.shape
nonzeros = np.sum(qnmat == mps.qntot)
logger.debug(f"Hmat dim: {nonzeros}")
# center mo
cmo = [asxp(mpo[idx]) for idx in cidx]
if qnmat.size > 1000 and algo != "direct":
# iterative algorithm
# diagonal elements of H
if omega is None:
tmp_ltensor = xp.einsum("aba -> ba", ltensor)
tmp_cmo0 = xp.einsum("abbc -> abc", cmo[0])
tmp_rtensor = xp.einsum("aba -> ba", rtensor)
if method == "1site":
# S-a c f-S
# O-b-O-g-O
# S-a c f-S
path = [([0, 1], "ba, bcg -> acg"),
([1, 0], "acg, gf -> acf")]
hdiag = multi_tensor_contract(
path, tmp_ltensor, tmp_cmo0,
tmp_rtensor)[(qnmat == mps.qntot)]
else:
# S-a c d f-S
# O-b-O-e-O-g-O
# S-a c d f-S
tmp_cmo1 = xp.einsum("abbc -> abc", cmo[1])
path = [
([0, 1], "ba, bce -> ace"),
([0, 1], "edg, gf -> edf"),
([0, 1], "ace, edf -> acdf"),
]
hdiag = multi_tensor_contract(
path, tmp_ltensor, tmp_cmo0, tmp_cmo1,
tmp_rtensor)[(qnmat == mps.qntot)]
else:
if method == "1site":
# S-a d h-S
# O-b-O-f-O
# | e |
# O-c-O-g-O
# S-a d h-S
hdiag = oe.contract(
"abca, bdef, cedg, hfgh -> adh",
ltensor,
cmo[0],
cmo[0],
rtensor,
backend=oe_backend)[(qnmat == mps.qntot)]
else:
# S-a d h l-S
# O-b-O-f-O-j-O
# | e i |
# O-c-O-g-O-k-O
# S-a d h l-S
hdiag = oe.contract(
"abca, bdef, cedg, fhij, gihk, ljkl -> adhl",
ltensor,
cmo[0],
cmo[0],
cmo[1],
cmo[1],
rtensor,
backend=oe_backend)[(qnmat == mps.qntot)]
hdiag = asnumpy(hdiag * inverse)
# initial guess
if method == "1site":
# initial guess b-S-c
# a
if nroots == 1:
cguess = [asnumpy(mps[cidx[0]])[qnmat == mps.qntot]]
else:
cguess = []
if averaged_ms is not None:
for ms in averaged_ms:
cguess.append(asnumpy(ms)[qnmat == mps.qntot])
else:
# initial guess b-S-c-S-e
# a d
if nroots == 1:
cguess = [
asnumpy(
tensordot(mps[cidx[0]], mps[cidx[1]],
axes=1)[qnmat == mps.qntot])
]
else:
cguess = []
if averaged_ms is not None:
for ms in averaged_ms:
if mps.to_right:
cguess.append(
asnumpy(
tensordot(
ms, mps[cidx[1]],
axes=1)[qnmat == mps.qntot]))
else:
cguess.append(
asnumpy(
tensordot(
mps[cidx[0]], ms,
axes=1)[qnmat == mps.qntot]))
if omega is not None:
if method == "1site":
# S-a e j-S
# O-b-O-g-O
# | f |
# O-c-O-i-O
# S-d h k-S
expr = oe.contract_expression(
"abcd, befg, cfhi, jgik, aej -> dhk",
ltensor,
cmo[0],
cmo[0],
rtensor,
cshape,
constants=[0, 1, 2, 3])
else:
# S-a e j o-S
# O-b-O-g-O-l-O
# | f k |
# O-c-O-i-O-n-O
# S-d h m p-S
expr = oe.contract_expression(
"abcd, befg, cfhi, gjkl, ikmn, olnp, aejo -> dhmp",
ltensor,
cmo[0],
cmo[0],
cmo[1],
cmo[1],
rtensor,
cshape,
constants=[0, 1, 2, 3, 4, 5])
count = 0
def hop(x):
nonlocal count
count += 1
clist = []
if x.ndim == 1:
clist.append(x)
else:
for icol in range(x.shape[1]):
clist.append(x[:, icol])
res = []
for c in clist:
# convert c to initial structure according to qn pattern
cstruct = asxp(cvec2cmat(cshape, c, qnmat, mps.qntot))
if omega is None:
if method == "1site":
# S-a l-S
# d
# O-b-O-f-O
# e
# S-c k-S
path = [
([0, 1], "abc, adl -> bcdl"),
([2, 0], "bcdl, bdef -> clef"),
([1, 0], "clef, lfk -> cek"),
]
cout = multi_tensor_contract(
path, ltensor, cstruct, cmo[0], rtensor)
else:
# S-a l-S
# d g
# O-b-O-f-O-j-O
# e h
# S-c k-S
path = [
([0, 1], "abc, adgl -> bcdgl"),
([3, 0], "bcdgl, bdef -> cglef"),
([2, 0], "cglef, fghj -> clehj"),
([1, 0], "clehj, ljk -> cehk"),
]
cout = multi_tensor_contract(
path,
ltensor,
cstruct,
cmo[0],
cmo[1],
rtensor,
)
else:
cout = expr(cstruct, backend=oe_backend)
# convert structure c to 1d according to qn
res.append(asnumpy(cout)[qnmat == mps.qntot])
if len(res) == 1:
return inverse * res[0]
else:
return inverse * np.stack(res, axis=1)
if len(cguess) < nroots:
cguess.extend([
np.random.random([nonzeros]) - 0.5
for i in range(len(cguess), nroots)
])
if algo == "davidson":
precond = lambda x, e, *args: x / (hdiag - e + 1e-4)
e, c = davidson(hop,
cguess,
precond,
max_cycle=100,
nroots=nroots,
max_memory=64000)
# if one root, davidson return e as np.float
#elif algo == "arpack":
# # scipy arpack solver : much slower than pyscf/davidson
# A = scipy.sparse.linalg.LinearOperator((nonzeros,nonzeros), matvec=hop)
# e, c = scipy.sparse.linalg.eigsh(A, k=nroots, which="SA", v0=cguess)
# # scipy return numpy.array
# if nroots == 1:
# e = e[0]
#elif algo == "lobpcg":
# precond = lambda x: scipy.sparse.diags(1/(hdiag+1e-4)) @ x
# A = scipy.sparse.linalg.LinearOperator((nonzeros,nonzeros),
# matvec=hop, matmat=hop)
# M = scipy.sparse.linalg.LinearOperator((nonzeros,nonzeros),
# matvec=precond, matmat=hop)
# e, c = scipy.sparse.linalg.lobpcg(A, np.array(cguess).T,
# M=M, largest=False)
elif algo == "primme":
precond = lambda x: scipy.sparse.diags(1 /
(hdiag + 1e-4)) @ x
A = scipy.sparse.linalg.LinearOperator(
(nonzeros, nonzeros), matvec=hop, matmat=hop)
M = scipy.sparse.linalg.LinearOperator(
(nonzeros, nonzeros), matvec=precond, matmat=hop)
e, c = primme.eigsh(A,
k=min(nroots, nonzeros),
which="SA",
v0=np.array(cguess).T,
OPinv=M,
method="PRIMME_DYNAMIC",
tol=1e-6)
else:
assert False
logger.debug(f"use {algo}, HC hops: {count}")
else:
logger.debug(f"use direct eigensolver")
# direct algorithm
if omega is None:
if method == "1site":
# S-a l-S
# d
# O-b-O-f-O
# e
# S-c k-S
ham = oe.contract("abc,bdef,lfk->adlcek",
ltensor,
cmo[0],
rtensor,
backend=oe_backend)
ham = ham[:, :, :, qnmat == mps.qntot][
qnmat == mps.qntot, :] * inverse
else:
# S-a l-S
# d g
# O-b-O-f-O-j-O
# e h
# S-c k-S
ham = oe.contract("abc,bdef,fghj,ljk->adglcehk",
ltensor, cmo[0], cmo[1], rtensor)
ham = ham[:, :, :, :, qnmat == mps.qntot][
qnmat == mps.qntot, :] * inverse
else:
if method == "1site":
# S-a e j-S
# O-b-O-g-O
# | f |
# O-c-O-i-O
# S-d h k-S
ham = oe.contract("abcd, befg, cfhi, jgik -> aejdhk",
ltensor, cmo[0], cmo[0], rtensor)
ham = ham[:, :, :, qnmat == mps.qntot][
qnmat == mps.qntot, :] * inverse
else:
# S-a e j o-S
# O-b-O-g-O-l-O
# | f k |
# O-c-O-i-O-n-O
# S-d h m p-S
ham = oe.contract(
"abcd, befg, cfhi, gjkl, ikmn, olnp -> aejodhmp",
ltensor, cmo[0], cmo[0], cmo[1], cmo[1], rtensor)
ham = ham[:, :, :, :, qnmat == mps.qntot][
qnmat == mps.qntot, :] * inverse
w, v = scipy.linalg.eigh(asnumpy(ham))
if nroots == 1:
e = w[0]
c = v[:, 0]
else:
e = w[:nroots]
c = [
v[:, iroot] for iroot in range(min(nroots, v.shape[1]))
]
# if multi roots, both davidson and primme return np.ndarray
if nroots > 1:
e = e.tolist()
logger.debug(f"energy: {e}")
micro_iteration_result.append(e)
cstruct = cvec2cmat(cshape, c, qnmat, mps.qntot, nroots=nroots)
# store the "optimal" mps (usually in the middle of each sweep)
if res_mps_idx is not None and res_mps_idx == imps:
if nroots == 1:
res_mps = mps.copy()
res_mps._update_mps(cstruct, cidx, qnbigl, qnbigr, mmax,
percent)
else:
res_mps = [mps.copy() for i in range(len(cstruct))]
for iroot in range(len(cstruct)):
res_mps[iroot]._update_mps(cstruct[iroot], cidx,
qnbigl, qnbigr, mmax,
percent)
averaged_ms = mps._update_mps(cstruct, cidx, qnbigl, qnbigr, mmax,
percent)
mps._switch_direction()
res_mps_idx = micro_iteration_result.index(min(micro_iteration_result))
macro_iteration_result.append(micro_iteration_result[res_mps_idx])
# check if convergence
if isweep > 0 and percent == 0:
v1, v2 = sorted(macro_iteration_result)[:2]
if np.allclose(v1,
v2,
rtol=mps.optimize_config.e_rtol,
atol=mps.optimize_config.e_atol):
converged = True
break
logger.debug(
f"{isweep+1} sweeps are finished, lowest energy = {sorted(macro_iteration_result)[0]}"
)
if converged:
logger.info("DMRG is converged!")
else:
logger.warning("DMRG is not converged! Please increase the procedure!")
logger.info(
f"The lowest two energies: {sorted(macro_iteration_result)[:2]}.")
# remove the redundant basis near the edge
if nroots == 1:
res_mps = res_mps.normalize().ensure_left_canon().canonicalise()
logger.info(f"{res_mps}")
else:
res_mps = [
mp.normalize().ensure_left_canon().canonicalise() for mp in res_mps
]
logger.info(f"{res_mps[0]}")
return macro_iteration_result, res_mps
def optimize_mps_dmrg(mps, mpo):
"""
1 or 2 site optimization procedure
"""
method = mps.optimize_config.method
procedure = mps.optimize_config.procedure
inverse = mps.optimize_config.inverse
nroots = mps.optimize_config.nroots
assert method in ["2site", "1site"]
# print("optimization method", method)
nexciton = mps.nexciton
# construct the environment matrix
environ = Environ(mps, mpo, "L")
nMPS = len(mps)
# construct each sweep cycle scheme
if method == "1site":
loop = [["R", i] for i in range(nMPS - 1, -1, -1)] + [
["L", i] for i in range(0, nMPS)
]
else:
loop = [["R", i] for i in range(nMPS - 1, 0, -1)] + [
["L", i] for i in range(1, nMPS)
]
# initial matrix
ltensor = ones((1, 1, 1))
rtensor = ones((1, 1, 1))
energies = []
for isweep, (mmax, percent) in enumerate(procedure):
logger.debug(f"mmax, percent: {mmax}, {percent}")
logger.debug(f"energy: {mps.expectation(mpo)}")
logger.debug(f"{mps}")
for system, imps in loop:
if system == "R":
lmethod, rmethod = "Enviro", "System"
else:
lmethod, rmethod = "System", "Enviro"
if method == "1site":
lsite = imps - 1
addlist = [imps]
else:
lsite = imps - 2
addlist = [imps - 1, imps]
ltensor = environ.GetLR(
"L", lsite, mps, mpo, itensor=ltensor, method=lmethod
)
rtensor = environ.GetLR(
"R", imps + 1, mps, mpo, itensor=rtensor, method=rmethod
)
# get the quantum number pattern
qnmat, qnbigl, qnbigr = svd_qn.construct_qnmat(
mps, mpo.pbond_list, addlist, method, system
)
cshape = qnmat.shape
# hdiag
tmp_ltensor = xp.einsum("aba -> ba", asxp(ltensor))
tmp_MPOimps = xp.einsum("abbc -> abc", asxp(mpo[imps]))
tmp_rtensor = xp.einsum("aba -> ba", asxp(rtensor))
if method == "1site":
# S-a c f-S
# O-b-O-g-O
# S-a c f-S
path = [([0, 1], "ba, bcg -> acg"), ([1, 0], "acg, gf -> acf")]
hdiag = multi_tensor_contract(
path, tmp_ltensor, tmp_MPOimps, tmp_rtensor
)[(qnmat == nexciton)]
# initial guess b-S-c
# a
cguess = mps[imps][qnmat == nexciton].array
else:
# S-a c d f-S
# O-b-O-e-O-g-O
# S-a c d f-S
tmp_MPOimpsm1 = xp.einsum("abbc -> abc", asxp(mpo[imps - 1]))
path = [
([0, 1], "ba, bce -> ace"),
([0, 1], "edg, gf -> edf"),
([0, 1], "ace, edf -> acdf"),
]
hdiag = multi_tensor_contract(
path, tmp_ltensor, tmp_MPOimpsm1, tmp_MPOimps, tmp_rtensor
)[(qnmat == nexciton)]
# initial guess b-S-c-S-e
# a d
cguess = asnumpy(tensordot(mps[imps - 1], mps[imps], axes=1)[qnmat == nexciton])
hdiag *= inverse
nonzeros = np.sum(qnmat == nexciton)
# print("Hmat dim", nonzeros)
mo1 = asxp(mpo[imps-1])
mo2 = asxp(mpo[imps])
def hop(c):
# convert c to initial structure according to qn pattern
cstruct = asxp(svd_qn.cvec2cmat(cshape, c, qnmat, nexciton))
if method == "1site":
# S-a l-S
# d
# O-b-O-f-O
# e
# S-c k-S
path = [
([0, 1], "abc, adl -> bcdl"),
([2, 0], "bcdl, bdef -> clef"),
([1, 0], "clef, lfk -> cek"),
]
cout = multi_tensor_contract(
path, ltensor, cstruct, mo2, rtensor
)
# for small matrices, check hermite:
# a=tensordot(ltensor, mpo[imps], ((1), (0)))
# b=tensordot(a, rtensor, ((4), (1)))
# c=b.transpose((0, 2, 4, 1, 3, 5))
# d=c.reshape(16, 16)
else:
# S-a l-S
# d g
# O-b-O-f-O-j-O
# e h
# S-c k-S
path = [
([0, 1], "abc, adgl -> bcdgl"),
([3, 0], "bcdgl, bdef -> cglef"),
([2, 0], "cglef, fghj -> clehj"),
([1, 0], "clehj, ljk -> cehk"),
]
cout = multi_tensor_contract(
path,
ltensor,
cstruct,
mo1,
mo2,
rtensor,
)
# convert structure c to 1d according to qn
return inverse * asnumpy(cout)[qnmat == nexciton]
if nroots != 1:
cguess = [cguess]
for iroot in range(nroots - 1):
cguess.append(np.random.random([nonzeros]) - 0.5)
precond = lambda x, e, *args: x / (asnumpy(hdiag) - e + 1e-4)
e, c = davidson(
hop, cguess, precond, max_cycle=100, nroots=nroots, max_memory=64000
)
# scipy arpack solver : much slower than davidson
# A = spslinalg.LinearOperator((nonzeros,nonzeros), matvec=hop)
# e, c = spslinalg.eigsh(A,k=1, which="SA",v0=cguess)
# print("HC loops:", count[0])
# logger.debug(f"isweep: {isweep}, e: {e}")
energies.append(e)
cstruct = svd_qn.cvec2cmat(cshape, c, qnmat, nexciton, nroots=nroots)
if nroots == 1:
# direct svd the coefficient matrix
mt, mpsdim, mpsqn, compmps = renormalization_svd(
cstruct,
qnbigl,
qnbigr,
system,
nexciton,
Mmax=mmax,
percent=percent,
)
else:
# diagonalize the reduced density matrix
mt, mpsdim, mpsqn, compmps = renormalization_ddm(
cstruct,
qnbigl,
qnbigr,
system,
nexciton,
Mmax=mmax,
percent=percent,
)
if method == "1site":
mps[imps] = mt
if system == "L":
if imps != len(mps) - 1:
mps[imps + 1] = tensordot(compmps, mps[imps + 1].array, axes=1)
mps.qn[imps + 1] = mpsqn
else:
mps[imps] = tensordot(mps[imps].array, compmps, axes=1)
mps.qn[imps + 1] = [0]
else:
if imps != 0:
mps[imps - 1] = tensordot(mps[imps - 1].array, compmps, axes=1)
mps.qn[imps] = mpsqn
else:
mps[imps] = tensordot(compmps, mps[imps].array, axes=1)
mps.qn[imps] = [0]
else:
if system == "L":
mps[imps - 1] = mt
mps[imps] = compmps
else:
mps[imps] = mt
mps[imps - 1] = compmps
# mps.dim_list[imps] = mpsdim
mps.qn[imps] = mpsqn
energies = np.array(energies)
if nroots == 1:
logger.debug("Optimization complete, lowest energy = %g", energies.min())
return energies