양자 회로를 이용해 양자 물질에서의 중성자 산란을 시뮬레이션한다

import timeit
import warnings
from collections.abc import Iterator, Sequence
from functools import partial

import matplotlib.pyplot as plt
import numpy as np
import quimb.tensor as qtn
import scipy.optimize
from numpy.typing import NDArray
from qiskit import QuantumCircuit
from qiskit.circuit import CircuitInstruction, ParameterVector, Qubit
from qiskit.circuit.library import PauliEvolutionGate
from qiskit.primitives import StatevectorEstimator
from qiskit.quantum_info import SparsePauliOp
from qiskit.transpiler.preset_passmanagers import generate_preset_pass_manager
from qiskit_addon_aqc_tensor import generate_ansatz_from_circuit
from qiskit_addon_aqc_tensor.objective import MaximizeStateFidelity
from qiskit_addon_aqc_tensor.simulation import tensornetwork_from_circuit
from qiskit_addon_aqc_tensor.simulation.quimb import QuimbSimulator
from qiskit_ibm_runtime import EstimatorV2 as Estimator
from qiskit_ibm_runtime import QiskitRuntimeService
from qiskit_quimb import quimb_circuit
from scipy.sparse import SparseEfficiencyWarning

# scipy.sparse.linalg.expm (reached via PauliEvolutionGate.to_matrix) prefers
# CSC and warns when handed the CSR matrix from SparsePauliOp.to_matrix; the
# result is unaffected, so silence the cosmetic warning.
warnings.filterwarnings("ignore", category=SparseEfficiencyWarning)


def xxz_hamiltonian_mpo(
    n_qubits: int, interaction: float = 1.0, anisotropy: float = 1.0
) -> qtn.MatrixProductOperator:
    """1D XXZ Hamiltonian as a quimb MPO.

    Builds the Hamiltonian using ``qtn.SpinHam1D``.

    Args:
        n_qubits: Number of sites.
        interaction: Overall interaction strength (J in the paper).
        anisotropy: XY/Z anisotropy (ε in the paper). ``ε = 1`` is the
            isotropic Heisenberg point; ``ε = 0`` is the Ising limit.

    Returns:
        The Hamiltonian as a matrix product operator.
    """
    builder = qtn.SpinHam1D(S=1 / 2)
    builder += interaction * anisotropy * 0.5, "+", "-"
    builder += interaction * anisotropy * 0.5, "-", "+"
    builder += interaction, "Z", "Z"
    return builder.build_mpo(L=n_qubits)


def build_ground_state_ansatz(n_qubits: int, n_layers: int) -> QuantumCircuit:
    """Hamiltonian variational ansatz (HVA) circuit for ground-state preparation.

    Starts from a product of singlet pairs and applies alternating
    odd/even layers of parameterized XXZ pair-evolution gates.

    The returned circuit is parameterized: it carries a ``ParameterVector``
    named ``"theta"`` of length ``2 * n_layers`` whose values must be
    assigned (e.g. via ``circuit.assign_parameters``) before simulation.
    Element ``2 * r`` is the odd-layer angle and element ``2 * r + 1`` is the
    even-layer angle of layer ``r``.

    Args:
        n_qubits: Number of qubits (must be even).
        n_layers: Number of HVA layers.

    Returns:
        The parameterized HVA preparation circuit.
    """
    theta = ParameterVector("theta", 2 * n_layers)
    circuit = QuantumCircuit(n_qubits)
    # Initial singlet product state
    for i in range(n_qubits // 2):
        circuit.x(2 * i)
        circuit.x(2 * i + 1)
        circuit.h(2 * i + 1)
        circuit.cx(2 * i + 1, 2 * i)
    # Variational layers: each pair gate is exp(-i theta (XX+YY+ZZ)/2)
    pair_ham = SparsePauliOp(
        ["XX", "YY", "ZZ"], coeffs=[0.5, 0.5, 0.5]
    )  # H_pair (HVA form)
    for r in range(n_layers):
        for i in range(1, (n_qubits + 1) // 2):  # odd layer
            circuit.append(
                PauliEvolutionGate(pair_ham, time=theta[2 * r]),
                [2 * i - 1, 2 * i],
            )
        for i in range(n_qubits // 2):  # even layer
            circuit.append(
                PauliEvolutionGate(pair_ham, time=theta[2 * r + 1]),
                [2 * i, 2 * i + 1],
            )
    return circuit


def optimize_ground_state_ansatz(
    ansatz: QuantumCircuit,
    x0: NDArray[np.floating],
    target_mps: qtn.MatrixProductState,
    *,
    max_bond: int | None = None,
    cutoff: float = 1e-10,
    method: str = "COBYQA",
    options: dict | None = None,
) -> scipy.optimize.OptimizeResult:
    """Optimize HVA parameters by maximizing fidelity with a target MPS.

    The HVA circuit is simulated as a matrix product state with the given
    bond-dimension truncation, and the parameters are optimized to maximize
    the state fidelity ``|<psi_HVA | target_mps>|**2`` with the DMRG ground
    state. Both states are normalized, so the minimized objective is the
    infidelity ``1 - |<psi_HVA | target_mps>|**2``.

    Args:
        ansatz: Parameterized HVA circuit from ``build_ground_state_ansatz``.
            The length of ``x0`` must equal ``ansatz.num_parameters``.
        x0: Initial parameters.
        target_mps: Target MPS (DMRG ground state) to maximize fidelity with.
        max_bond: Maximum MPS bond dimension during gate application.
        cutoff: Singular-value cutoff during gate application.
        method: ``scipy.optimize.minimize`` method.
        options: Options dict forwarded to ``scipy.optimize.minimize``.

    Returns:
        The Scipy OptimizeResult.
    """

    def infidelity(params: NDArray[np.floating]) -> float:
        circuit = ansatz.assign_parameters(params)
        circuit_mps = quimb_circuit(
            circuit.decompose(["PauliEvolution"]),
            quimb_circuit_class=qtn.CircuitMPS,
            max_bond=max_bond,
            cutoff=cutoff,
        )
        return 1 - abs(circuit_mps.psi.H @ target_mps) ** 2

    return scipy.optimize.minimize(
        infidelity, np.asarray(x0), method=method, options=options
    )


def trotter_evolution(
    qubits: Sequence[Qubit],
    interaction: float,
    anisotropy: float,
    time_step: float,
    n_steps: int,
) -> Iterator[CircuitInstruction]:
    """Second-order Trotter steps of the XXZ pair Hamiltonian.

    While the paper used a hand-optimized circuit for the Trotter steps, we use
    PauliEvolutionGate here for simplicity and generality. The final two-qubit gate
    count and gate depth are equivalent when transpiled with ``optimization_level=3``.

    Args:
        qubits: Qubits to act on (length ``n_qubits``).
        interaction: Overall interaction strength (J in the paper).
        anisotropy: XY/Z anisotropy (ε in the paper). ``ε = 1`` is the
            isotropic Heisenberg point; ``ε = 0`` is the Ising limit.
        time_step: Per-step Trotter time.
        n_steps: Number of Trotter steps.

    Yields:
        ``CircuitInstruction``s implementing the Trotter steps.
    """
    if n_steps == 0:
        return
    n_qubits = len(qubits)
    pair_ham = SparsePauliOp(
        ["XX", "YY", "ZZ"],
        coeffs=[
            0.25 * interaction * anisotropy,
            0.25 * interaction * anisotropy,
            0.25 * interaction,
        ],
    )
    half_evo = PauliEvolutionGate(pair_ham, time=time_step / 2)
    full_evo = PauliEvolutionGate(pair_ham, time=time_step)
    for i in range(n_qubits // 2):  # half even layer
        yield CircuitInstruction(half_evo, (qubits[2 * i], qubits[2 * i + 1]))
    for i in range(n_qubits // 2 - 1):  # full odd layer
        yield CircuitInstruction(
            full_evo, (qubits[2 * i + 1], qubits[2 * i + 2])
        )
    for _ in range(n_steps - 1):  # interior steps
        for i in range(n_qubits // 2):
            yield CircuitInstruction(
                full_evo, (qubits[2 * i], qubits[2 * i + 1])
            )
        for i in range(n_qubits // 2 - 1):
            yield CircuitInstruction(
                full_evo, (qubits[2 * i + 1], qubits[2 * i + 2])
            )
    for i in range(n_qubits // 2):  # half even layer
        yield CircuitInstruction(half_evo, (qubits[2 * i], qubits[2 * i + 1]))


def get_dsf(
    n_qubits: int,
    rgf_mat: NDArray[np.floating],
    time_step: float,
    n_steps: int,
    n_points_momentum: int,
    n_points_frequency: int,
) -> NDArray[np.floating]:
    """Compute the dynamical structure factor from the retarded Green's function.

    Uses the center-site approximation and a discrete Fourier transform.
    The result is symmetrized about the momentum axis and clipped to
    non-negative values, ready for plotting.

    Args:
        n_qubits: Number of qubits (sites).
        rgf_mat: RGF matrix of shape ``(n_steps, n_qubits)``.
        time_step: Trotter time-step size.
        n_steps: Number of time steps.
        n_points_momentum: Number of momentum points.
        n_points_frequency: Number of frequency points.

    Returns:
        DSF array of shape ``(n_points_frequency, n_points_momentum)``,
        symmetrized about the momentum axis and clipped to non-negative values.
    """
    max_frequency = np.pi / time_step
    momentum_range = np.linspace(0, 2 * np.pi, n_points_momentum)
    frequency_range = np.linspace(0, max_frequency, n_points_frequency)
    result = np.zeros((frequency_range.shape[0], momentum_range.shape[0]))
    center = n_qubits // 2 - 1
    for iw, w in enumerate(frequency_range):
        exponent = np.exp(1j * w * time_step * np.arange(1, n_steps + 1))
        # S = sigma/2, so two spin operators contribute a factor of (1/2)(1/2) = 1/4.
        rgf_omega = (
            np.dot(rgf_mat.T, exponent) * time_step / 4
        )  # S(omega): time Fourier slice of the Green's function
        for iq, q in enumerate(momentum_range):
            momentum_phases = np.exp(
                -1j * q * np.arange(-center, center + 2, 1)
            )
            result[iw, iq] = np.imag(np.dot(rgf_omega, momentum_phases))
    result = -(result + result[:, ::-1]) / 2
    result = np.clip(result, a_min=0, a_max=None)
    return result


def plot_dsf(
    dsf: NDArray[np.floating],
    time_step: float,
    n_points_momentum: int,
    n_points_frequency: int,
    title: str | None = None,
) -> None:
    """Heat-map of the dynamical structure factor.

    Args:
        dsf: DSF array of shape ``(n_points_frequency, n_points_momentum)``.
        time_step: Trotter time-step size.
        n_points_momentum: Number of momentum points.
        n_points_frequency: Number of frequency points.
        title: Optional plot title.
    """
    max_frequency = np.pi / time_step
    momentum_range = np.linspace(0, 2 * np.pi, n_points_momentum)
    frequency_range = np.linspace(0, max_frequency, n_points_frequency)
    x, y = np.meshgrid(momentum_range, frequency_range)
    fig, ax = plt.subplots(figsize=(8, 5))
    c = ax.pcolormesh(x, y, dsf / np.max(dsf), cmap="viridis", shading="auto")
    fig.colorbar(c, ax=ax, label="Normalized intensity")
    ax.set_ylim(0, 3.6)
    ax.set_xlim(0, 2 * np.pi)
    ax.set_xlabel(r"$q$", fontsize=16)
    ax.set_ylabel(r"$\tilde{\omega} = \omega / J$", fontsize=16)
    ax.set_xticks([0, np.pi / 2, np.pi, 3 * np.pi / 2, 2 * np.pi])
    ax.set_xticklabels(["0", r"$\pi/2$", r"$\pi$", r"$3\pi/2$", r"$2\pi$"])
    if title:
        ax.set_title(title, fontsize=14)
    plt.tight_layout()
    plt.show()


def plot_rgf(
    n_qubits: int,
    rgf_mat: NDArray[np.floating],
    time_step: float,
    n_steps: int,
    title: str | None = None,
) -> None:
    """Heat-map of the retarded Green's function in real space and time.

    Args:
        n_qubits: Number of qubits (sites).
        rgf_mat: RGF matrix of shape ``(n_steps, n_qubits)``.
        time_step: Trotter time-step size.
        n_steps: Number of time steps.
        title: Optional plot title.
    """
    fig, ax = plt.subplots(figsize=(8, 6))
    qubit_axis = np.arange(n_qubits)
    t_axis = np.arange(1, n_steps + 1) * time_step
    x, y = np.meshgrid(qubit_axis, t_axis)
    c = ax.pcolormesh(
        x,
        y,
        np.real(rgf_mat),
        cmap="RdBu",
        vmax=0.5,
        vmin=-0.5,
        shading="auto",
    )
    fig.colorbar(c, ax=ax, label=r"Re $G^R(j, j_c, t)$")
    ax.set_xlabel("Qubit", fontsize=16)
    ax.xaxis.set_major_locator(
        plt.matplotlib.ticker.MaxNLocator(integer=True)
    )
    ax.set_ylabel(r"Time", fontsize=16)
    if title:
        ax.set_title(title, fontsize=14)
    plt.tight_layout()
    plt.show()


def uniform_2q_depth(circuit: QuantumCircuit) -> int:
    """Two-qubit gate depth in a standardized basis."""
    pass_manager = generate_preset_pass_manager(
        optimization_level=0, basis_gates=["cz", "id", "rz", "sx", "x"]
    )
    return pass_manager.run(circuit).depth(
        lambda inst: inst.operation.num_qubits == 2
    )

# -- Physical parameters --
n_qubits = 10
interaction = 1.0  # J
anisotropy = 1.0  # ε (isotropic point)
time_step = 0.6
n_steps = 10
mps_max_bond = 32
mps_cutoff = 1e-8
center = n_qubits // 2 - 1

# -- Hamiltonian MPO --
ham_mpo = xxz_hamiltonian_mpo(n_qubits, interaction, anisotropy)

# -- Reference ground-state energy via DMRG --
dmrg = qtn.DMRG2(ham_mpo)
dmrg.solve(tol=1e-8)
print(f"Ground-state energy (DMRG): {dmrg.energy:.6f}")

# -- Build ground state ansatz circuit --
gs_n_layers = 3
gs_ansatz = build_ground_state_ansatz(n_qubits, gs_n_layers)

# -- Optimize ground state ansatz parameters to maximize fidelity with the DMRG MPS --
# Initialize odd-layer angles near 0 (where the inter-pair gate is the
# identity) and even-layer angles near pi/2 (where the intra-pair gate
# is a SWAP, since 0.5*(XX + YY + ZZ) = SWAP - I/2).
rng = np.random.default_rng(12345)
x0 = np.tile([0, np.pi / 2], gs_n_layers) + rng.normal(
    scale=0.1, size=2 * gs_n_layers
)
print("Optimizing ground state ansatz...")
t0 = timeit.default_timer()
result = optimize_ground_state_ansatz(
    gs_ansatz,
    x0,
    dmrg.state,
    max_bond=mps_max_bond,
    cutoff=mps_cutoff,
    options=dict(maxiter=100),
)
t1 = timeit.default_timer()
print(f"Finished optimizing ground state ansatz in {t1 - t0} seconds.")
print(f"Ground state ansatz fidelity: {1 - result.fun:.6f}")

gs_circuit = gs_ansatz.assign_parameters(result.x)
gs_circuit_mps = quimb_circuit(
    gs_circuit.decompose(["PauliEvolution"]),
    quimb_circuit_class=qtn.CircuitMPS,
    max_bond=mps_max_bond,
    cutoff=mps_cutoff,
)
gs_ansatz_energy = qtn.expec_TN_1D(
    gs_circuit_mps.psi.H, ham_mpo, gs_circuit_mps.psi
)
print(f"Ground state ansatz energy: {gs_ansatz_energy:.6f}")

# -- Build circuits for each time step --
perturbed = gs_circuit.copy()
perturbed.rz(np.pi / 2, center)

circuits = []
for t in range(1, n_steps + 1):
    circuit = perturbed.copy()
    for instr in trotter_evolution(
        circuit.qubits, interaction, anisotropy, time_step, t
    ):
        circuit.append(instr)
    circuits.append(circuit)
print(
    f"Built {len(circuits)} circuits, deepest 2q depth (uniform basis) = "
    f"{uniform_2q_depth(circuits[-1])}"
)

# -- Observables: Z on each qubit site --
observables = [
    SparsePauliOp.from_sparse_list([("Z", [i], 1)], num_qubits=n_qubits)
    for i in range(n_qubits)
]
print(f"Defined {len(observables)} Z observables.")

# Number of time steps to compress into an AQC ansatz with one layer
aqc_n_steps_1 = 3
# Number of time steps to compress into an AQC ansatz with two layers
aqc_n_steps_2 = 2
aqc_n_steps_total = aqc_n_steps_1 + aqc_n_steps_2

# ── Step 2a: Target circuits (first aqc_n_steps_total circuits from Step 1) ──
target_circuits = {
    k: circuits[k - 1] for k in range(1, aqc_n_steps_total + 1)
}
# ── Step 2b: Compute target MPS ──
# Decompose PauliEvolutionGate to RXX/RYY/RZZ before passing to the AQC MPS
# backend, which does not understand PauliEvolutionGate natively.
aqc_sim = QuimbSimulator(
    quimb_circuit_factory=partial(
        qtn.CircuitMPS,
        gate_opts=dict(max_bond=mps_max_bond, cutoff=mps_cutoff),
    ),
    autodiff_backend="jax",
)
print("\nStep 2b — target MPS:")
target_mps = {}
for k in range(1, aqc_n_steps_total + 1):
    target_mps[k] = tensornetwork_from_circuit(
        target_circuits[k].decompose(["PauliEvolution"]), aqc_sim
    )
    print(f"  k={k}: max bond = {target_mps[k].psi.max_bond()}")

# ── Step 2c: Generate ansätze (one-layer and two-layer) and optimize parameters ──
ansatz_1, initial_params_1 = generate_ansatz_from_circuit(
    target_circuits[1].decompose(["PauliEvolution"]),
    qubits_initially_zero=True,
)
initial_params_1 = np.array(initial_params_1)
ansatz_2, initial_params_2 = generate_ansatz_from_circuit(
    target_circuits[2].decompose(["PauliEvolution"]),
    qubits_initially_zero=True,
)
initial_params_2 = np.array(initial_params_2)
print(
    f"\nStep 2c — one-layer ansatz: {ansatz_1.num_parameters} parameters, "
    f"2q depth (uniform basis) = {uniform_2q_depth(ansatz_1)}"
)
print(
    f"Step 2c — two-layer ansatz: {ansatz_2.num_parameters} parameters, "
    f"2q depth (uniform basis) = {uniform_2q_depth(ansatz_2)}"
)

aqc_circuits = {}
aqc_params = {}
for k in range(1, aqc_n_steps_total + 1):
    if k <= aqc_n_steps_1:
        ansatz, base_params = ansatz_1, initial_params_1
    else:
        ansatz, base_params = ansatz_2, initial_params_2
    # Warm-start from the previous step only within the same stage
    same_stage = (k - 1 >= 1) and (
        (k - 1 <= aqc_n_steps_1) == (k <= aqc_n_steps_1)
    )
    x0 = aqc_params[k - 1] if same_stage else base_params
    obj = MaximizeStateFidelity(target_mps[k], ansatz, aqc_sim)
    t0 = timeit.default_timer()
    result = scipy.optimize.minimize(
        obj.loss_function,
        x0,
        method="L-BFGS-B",
        jac=True,
        options=dict(maxiter=100),
    )
    elapsed = timeit.default_timer() - t0
    aqc_params[k] = result.x
    aqc_circuits[k] = ansatz.assign_parameters(result.x)
    print(
        f"  k={k}: fidelity = {1 - result.fun:.4f}, "
        f"2q depth (uniform basis) = "
        f"{uniform_2q_depth(aqc_circuits[k])}, "
        f"{elapsed:.1f}s"
    )

# ── Step 2d: Assemble full circuit set (AQC + Trotter) ──
all_circuits = []
for k in range(1, aqc_n_steps_total + 1):
    all_circuits.append(aqc_circuits[k])
base = aqc_circuits[aqc_n_steps_total]
for k in range(1, n_steps - aqc_n_steps_total + 1):
    circuit = base.copy()
    for instr in trotter_evolution(
        circuit.qubits, interaction, anisotropy, time_step, k
    ):
        circuit.append(instr)
    all_circuits.append(circuit)

full_depths = [
    uniform_2q_depth(circuits[k - 1]) for k in range(1, n_steps + 1)
]
aqc_depths = [uniform_2q_depth(circuit) for circuit in all_circuits]
full_2q = [
    circuits[k - 1].decompose(["PauliEvolution"]).num_nonlocal_gates()
    for k in range(1, n_steps + 1)
]
aqc_2q = [
    circuit.decompose(["PauliEvolution"]).num_nonlocal_gates()
    for circuit in all_circuits
]
print(f"\nStep 2d — assembled {len(all_circuits)} circuits")
print(
    f"  At step {n_steps} (uniform basis): "
    f"Trotter 2q depth = {full_depths[-1]}, AQC+Trotter 2q depth = {aqc_depths[-1]}; "
    f"2q gates: Trotter = {full_2q[-1]}, AQC+Trotter = {aqc_2q[-1]}"
)

steps_axis = np.arange(1, n_steps + 1)
fig, ax = plt.subplots(figsize=(7, 4))
ax.plot(steps_axis, full_depths, "-o", color="black", label="Full Trotter")
ax.plot(
    steps_axis, aqc_depths, "-o", color="cadetblue", label="AQC + Trotter"
)
ax.set_xlabel("Trotter steps", fontsize=13)
ax.xaxis.set_major_locator(plt.matplotlib.ticker.MaxNLocator(integer=True))
ax.set_ylabel("2q gate depth (uniform basis)", fontsize=13)
ax.set_title(f"AQC circuit-depth reduction ({n_qubits} qubits)", fontsize=13)
ax.legend(fontsize=11)
plt.tight_layout()
plt.show()

estimator = StatevectorEstimator()
pubs = [(circuit, observables) for circuit in all_circuits]
job = estimator.run(pubs)
result = job.result()

rgf_mat = np.stack([pub_result.data.evs for pub_result in result])

# -- Compute DSF --
n_points_momentum, n_points_frequency = 100, 100
spectrum = get_dsf(
    n_qubits,
    rgf_mat,
    time_step,
    n_steps,
    n_points_momentum,
    n_points_frequency,
)

# -- Plot retarded Green's function --
plot_rgf(
    n_qubits,
    rgf_mat,
    time_step,
    n_steps,
    title=f"Retarded Green's function — {n_qubits} qubits (simulation)",
)

# -- Plot DSF --
plot_dsf(
    spectrum,
    time_step,
    n_points_momentum,
    n_points_frequency,
    title=f"Dynamical structure factor — {n_qubits} qubits (simulation)",
)

# ── Parameters ──────────────────────────────────────────────────────────────
n_qubits = 50  # 10 → 50
interaction = 1.0  # J
anisotropy = 1.0  # ε (isotropic point)
time_step = 0.6
n_steps = 20  # 10 → 20
aqc_n_steps_1 = 6  # 3 → 6
aqc_n_steps_2 = 4  # 2 → 4
aqc_n_steps_total = aqc_n_steps_1 + aqc_n_steps_2
gs_n_layers = 5  # 3 → 5
mps_max_bond = 128  # 32 -> 128
mps_cutoff = 1e-8
center = n_qubits // 2 - 1

# ── Step 1: Map ──────────────────────────────────────────────────────────────
ham_mpo = xxz_hamiltonian_mpo(n_qubits, interaction, anisotropy)

dmrg = qtn.DMRG2(ham_mpo)
dmrg.solve(tol=1e-8)
print(f"Ground-state energy (DMRG): {dmrg.energy:.6f}")

gs_ansatz = build_ground_state_ansatz(n_qubits, gs_n_layers)

rng = np.random.default_rng(12345)
x0 = np.tile([0.0, np.pi / 2], gs_n_layers) + rng.normal(
    scale=0.1, size=2 * gs_n_layers
)
print("Optimizing ground state ansatz...")
t0 = timeit.default_timer()
result = optimize_ground_state_ansatz(
    gs_ansatz,
    x0,
    dmrg.state,
    max_bond=mps_max_bond,
    cutoff=mps_cutoff,
    options=dict(maxiter=100),
)
t1 = timeit.default_timer()
print(f"Finished optimizing ground state ansatz in {t1 - t0} seconds.")
print(f"Ground state ansatz fidelity: {1 - result.fun:.6f}")

gs_circuit = gs_ansatz.assign_parameters(result.x)
gs_circuit_mps = quimb_circuit(
    gs_circuit.decompose(["PauliEvolution"]),
    quimb_circuit_class=qtn.CircuitMPS,
    max_bond=mps_max_bond,
    cutoff=mps_cutoff,
)
gs_ansatz_energy = qtn.expec_TN_1D(
    gs_circuit_mps.psi.H, ham_mpo, gs_circuit_mps.psi
)
print(f"Ground state ansatz energy: {gs_ansatz_energy:.6f}")

perturbed = gs_circuit.copy()
perturbed.rz(np.pi / 2, center)

circuits = []
for t in range(1, n_steps + 1):
    circuit = perturbed.copy()
    for instr in trotter_evolution(
        circuit.qubits, interaction, anisotropy, time_step, t
    ):
        circuit.append(instr)
    circuits.append(circuit)
print(
    f"Built {len(circuits)} circuits, deepest 2q depth (uniform basis) = "
    f"{uniform_2q_depth(circuits[-1])}"
)

observables = [
    SparsePauliOp.from_sparse_list([("Z", [i], 1)], num_qubits=n_qubits)
    for i in range(n_qubits)
]
print(f"Defined {len(observables)} Z observables.")

# ── Step 2: AQC ──────────────────────────────────────────────────────────────
target_circuits = {
    k: circuits[k - 1] for k in range(1, aqc_n_steps_total + 1)
}

aqc_sim = QuimbSimulator(
    quimb_circuit_factory=partial(
        qtn.CircuitMPS,
        gate_opts=dict(max_bond=mps_max_bond, cutoff=mps_cutoff),
    ),
    autodiff_backend="jax",
)
print("\nStep 2b — target MPS:")
target_mps = {}
for k in range(1, aqc_n_steps_total + 1):
    target_mps[k] = tensornetwork_from_circuit(
        target_circuits[k].decompose(["PauliEvolution"]), aqc_sim
    )
    print(f"  k={k}: max bond = {target_mps[k].psi.max_bond()}")

ansatz_1, initial_params_1 = generate_ansatz_from_circuit(
    target_circuits[1].decompose(["PauliEvolution"]),
    qubits_initially_zero=True,
)
initial_params_1 = np.array(initial_params_1)
ansatz_2, initial_params_2 = generate_ansatz_from_circuit(
    target_circuits[2].decompose(["PauliEvolution"]),
    qubits_initially_zero=True,
)
initial_params_2 = np.array(initial_params_2)
print(
    f"\nStep 2c — one-layer ansatz: {ansatz_1.num_parameters} parameters, "
    f"2q depth (uniform basis) = {uniform_2q_depth(ansatz_1)}"
)
print(
    f"Step 2c — two-layer ansatz: {ansatz_2.num_parameters} parameters, "
    f"2q depth (uniform basis) = {uniform_2q_depth(ansatz_2)}"
)

aqc_circuits = {}
aqc_params = {}
for k in range(1, aqc_n_steps_total + 1):
    if k <= aqc_n_steps_1:
        ansatz, base_params = ansatz_1, initial_params_1
    else:
        ansatz, base_params = ansatz_2, initial_params_2
    # Warm-start from the previous step only within the same stage
    same_stage = (k - 1 >= 1) and (
        (k - 1 <= aqc_n_steps_1) == (k <= aqc_n_steps_1)
    )
    x0 = aqc_params[k - 1] if same_stage else base_params
    obj = MaximizeStateFidelity(target_mps[k], ansatz, aqc_sim)
    t0 = timeit.default_timer()
    result = scipy.optimize.minimize(
        obj.loss_function,
        x0,
        method="L-BFGS-B",
        jac=True,
        options=dict(maxiter=100),
    )
    elapsed = timeit.default_timer() - t0
    aqc_params[k] = result.x
    aqc_circuits[k] = ansatz.assign_parameters(result.x)
    print(
        f"  k={k}: fidelity = {1 - result.fun:.4f}, "
        f"2q depth (uniform basis) = "
        f"{uniform_2q_depth(aqc_circuits[k])}, "
        f"{elapsed:.1f}s"
    )

all_circuits = []
for k in range(1, aqc_n_steps_total + 1):
    all_circuits.append(aqc_circuits[k])
base = aqc_circuits[aqc_n_steps_total]
for k in range(1, n_steps - aqc_n_steps_total + 1):
    circuit = base.copy()
    for instr in trotter_evolution(
        circuit.qubits, interaction, anisotropy, time_step, k
    ):
        circuit.append(instr)
    all_circuits.append(circuit)

full_depths = [
    uniform_2q_depth(circuits[k - 1]) for k in range(1, n_steps + 1)
]
aqc_depths = [uniform_2q_depth(circuit) for circuit in all_circuits]
full_2q = [
    circuits[k - 1].decompose(["PauliEvolution"]).num_nonlocal_gates()
    for k in range(1, n_steps + 1)
]
aqc_2q = [
    circuit.decompose(["PauliEvolution"]).num_nonlocal_gates()
    for circuit in all_circuits
]
print(f"\nStep 2d — assembled {len(all_circuits)} circuits")
print(
    f"  At step {n_steps} (uniform basis): "
    f"Trotter 2q depth = {full_depths[-1]}, AQC+Trotter 2q depth = {aqc_depths[-1]}; "
    f"2q gates: Trotter = {full_2q[-1]}, AQC+Trotter = {aqc_2q[-1]}"
)

steps_axis = np.arange(1, n_steps + 1)
fig, ax = plt.subplots(figsize=(7, 4))
ax.plot(steps_axis, full_depths, "-o", color="black", label="Full Trotter")
ax.plot(
    steps_axis, aqc_depths, "-o", color="cadetblue", label="AQC + Trotter"
)
ax.set_xlabel("Trotter steps", fontsize=13)
ax.xaxis.set_major_locator(plt.matplotlib.ticker.MaxNLocator(integer=True))
ax.set_ylabel("2q gate depth (uniform basis)", fontsize=13)
ax.set_title(f"AQC circuit-depth reduction ({n_qubits} qubits)", fontsize=13)
ax.legend(fontsize=11)
plt.tight_layout()
plt.show()

# ── Step 3: Execute on IBM Quantum hardware ───────────────────────────────────
# (replaces StatevectorEstimator)
service = QiskitRuntimeService()
backend = service.least_busy(
    min_num_qubits=n_qubits,
    operational=True,
    simulator=False,
    filters=lambda x: x.configuration().processor_type["family"] == "Heron",
)
print(f"Backend: {backend.name}")

pm = generate_preset_pass_manager(optimization_level=3, backend=backend)
isa_circuits = pm.run(all_circuits, num_processes=1)
isa_2q_depths = [
    isa_circuit.depth(lambda inst: inst.operation.num_qubits == 2)
    for isa_circuit in isa_circuits
]
print(
    f"Transpiled 2q depth (deepest, ISA on {backend.name}): "
    f"{max(isa_2q_depths)} "
    f"(2q gates: {max(isa_circuit.num_nonlocal_gates() for isa_circuit in isa_circuits)})"
)

estimator = Estimator(backend)
estimator.options.environment.job_tags = ["TUT_SNS"]
estimator.options.dynamical_decoupling.enable = True
estimator.options.dynamical_decoupling.sequence_type = "XY4"
estimator.options.twirling.enable_gates = True
estimator.options.twirling.num_randomizations = 1000
estimator.options.twirling.shots_per_randomization = 128
estimator.options.resilience.measure_mitigation = True
estimator.options.resilience.measure_noise_learning.num_randomizations = 32
estimator.options.resilience.measure_noise_learning.shots_per_randomization = 100

pubs = [
    (
        isa_circuit,
        [obs.apply_layout(isa_circuit.layout) for obs in observables],
    )
    for isa_circuit in isa_circuits
]
job = estimator.run(pubs)
print(f"Job ID: {job.job_id()}")

result = job.result()

# ── Step 4: Post-process ──────────────────────────────────────────────────────
rgf_mat = np.stack([pub_result.data.evs for pub_result in result])

n_points_momentum, n_points_frequency = 100, 100
spectrum = get_dsf(
    n_qubits,
    rgf_mat,
    time_step,
    n_steps,
    n_points_momentum,
    n_points_frequency,
)

plot_rgf(
    n_qubits,
    rgf_mat,
    time_step,
    n_steps,
    title=f"Retarded Green's function — {n_qubits} qubits (QPU)",
)
plot_dsf(
    spectrum,
    time_step,
    n_points_momentum,
    n_points_frequency,
    title=rf"KCuF$_3$ DSF — {n_qubits} qubits (QPU)"
    "\n(AQC + DD + Pauli twirling + TREX)",
)