Variational quantum machine learning (VQML) combines parameterized quantum circuits with classical optimization to train models on data-dependent cost functions. A central practical challenge in this workflow is that gradient evaluation can become a major computational bottleneck, and different quantum software frameworks provide different differentiation strategies. This paper shows that, in the tested statevector simulation setting, the choice of differentiation method has a stronger effect on one full gradient computation than the framework choice alone. To demonstrate this, the benchmark compares three configurations: Qiskit parameter-shift using Aer, PennyLane parameter-shift using lightning.qubit, and PennyLane adjoint differentiation using lightning.qubit. All configurations use the same four-qubit hardware-efficient ansatz, the same observable, and the same parameter scaling with circuit depth. Runtime is measured across increasing ansatz sizes, where increasing the number of layers also increases the number of trainable parameters and the circuit depth. The results show that simulator-specific adjoint differentiation scales substantially more efficiently than parameter-shift in this setting, while the comparison between Qiskit and PennyLane parameter-shift shows additional workflow-level performance differences under the same general differentiation rule. At 808 trainable parameters, PennyLane adjoint averaged 0.0598s, compared with 7.56s for Qiskit parameter-shift and 23.14s for PennyLane parameter-shift, corresponding to 126× and 387× lower mean runtime, respectively.
Variational quantum machine learning (VQML) combines parameterized quantum circuits with classical optimization to train models on data-dependent cost functions. A central practical challenge in this workflow is that gradient evaluation can become a major computational bottleneck, and different quantum software frameworks provide different differentiation strategies. This paper shows that, in the tested statevector simulation setting, the choice of differentiation method has a stronger effect on one full gradient computation than the framework choice alone. To demonstrate this, the benchmark compares three configurations: Qiskit parameter-shift using Aer, PennyLane parameter-shift using lightning.qubit, and PennyLane adjoint differentiation using lightning.qubit. All configurations use the same four-qubit hardware-efficient ansatz, the same observable, and the same parameter scaling with circuit depth. Runtime is measured across increasing ansatz sizes, where increasing the number of layers also increases the number of trainable parameters and the circuit depth. The results show that simulator-specific adjoint differentiation scales substantially more efficiently than parameter-shift in this setting, while the comparison between Qiskit and PennyLane parameter-shift shows additional workflow-level performance differences under the same general differentiation rule. At 808 trainable parameters, PennyLane adjoint averaged 0.0598s, compared with 7.56s for Qiskit parameter-shift and 23.14s for PennyLane parameter-shift, corresponding to 126× and 387× lower mean runtime, respectively.
This study presents a reproducible, framework-level comparison of three open-source quantum software environments: PennyLane 0.45.1, Qiskit 2.5.2, and Snowflurry 0.6.0. Equivalent parameterized circuits were constructed in Python for PennyLane and Qiskit and in Julia for Snowflurry. Every circuit consisted of repeated layers of single-qubit rotations followed by a ring of controlled-NOT gates, and every framework returned the complete ideal statevector. Circuit construction time, first-execution time, warmed execution time, whole-process wall time, output probability, and state normalization were recorded. All common numerical thread controls were fixed to one, so the experiment measures controlled single-thread behavior rather than the maximum throughput of the tested computers. On the laptop, Snowflurry produced the lowest warmed median at 10 qubits, Qiskit at 12 qubits, PennyLane and Qiskit were nearly tied at 14 qubits, and PennyLane was fastest at 18 qubits. On an Intel Xeon E5-2697 v3 workstation, PennyLane was fastest at both 14 and 16 qubits. Snowflurry constructed circuits rapidly but exhibited greater simulation time as the statevector increased. Identical probabilities and unit state norms across all implementations support functional equivalence. The results characterize these particular built-in statevector paths; they do not constitute a general comparison of Python and Julia, nor of optimized accelerators such as PennyLane Lightning or Qiskit Aer.
Quantum machine learning (QML) has emerged as a promising field, combining the power of quantum computing with classical machine learning techniques to solve complex computational tasks. As the demand for efficient quantum simulations grows, multiple QML frameworks, including PennyLane, Qiskit, and TensorFlow Quantum (TFQ), have been developed to facilitate hybrid quantum-classical computations. This study aims to evaluate and compare the performance of three leading QML frameworks PennyLane, Qiskit, and TensorFlow Quantum in simulating quantum machine learning models, focusing on accuracy, execution time, and noise tolerance. The study examined three leading quantum machine learning (QML) frameworks PennyLane (v0.24), Qiskit (v0.43.2), and TensorFlow Quantum (TFQ, v0.7) each tested on a 64-bit Ubuntu Linux system with an Intel Core i7 processor, 32 GB RAM, and NVIDIA GeForce RTX 3080 GPU. Quantum algorithms like variational quantum circuits (VQCs) and quantum support vector machines (QSVMs) were simulated using these frameworks. Various quantum gates, including Pauli-X, Y, Z, Hadamard, CNOT, and Rotation gates (Rx, Ry, Rz), were used for parameter optimization and quantum superposition. The Iris and MNIST datasets were adapted for quantum encoding using Amplitude and Angle Encoding for binary classification tasks. Simulations were run on classical computers, while select circuits were executed on IBM Quantum’s Falcon r5.11 processor to compare hardware performance. PennyLane achieved the highest accuracy (92%) in quantum simulations, excelling in hybrid quantum-classical model integration. TensorFlow Quantum provided the fastest execution time, especially in classical simulations, making it suitable for rapid prototyping. Qiskit produced deeper quantum circuits but had higher error rates (6%) on real quantum hardware, highlighting noise and decoherence effects. The VQC models optimized by stochastic gradient descent (SGD) showed significant improvements in model performance, and QSVMs effectively classified both linearly separable and non-separable datasets, demonstrating the potential of quantum algorithms over classical approaches. Statistical analysis confirmed the significance of the results (p < 0.05). PennyLane is the most robust framework for hybrid quantum-classical models, while TensorFlow Quantum is suited for rapid prototyping. Qiskit, despite longer execution times, excels in hardware implementation. The choice of framework should align with the specific needs of quantum machine learning tasks.
Classical simulation supports the development and validation of quantum algorithms through full-state inspection, controlled noise models and backpropagation, albeit for small quantum systems. Existing frameworks offer gate-level execution, differentiable pulse-level dynamics or optimised hardware execution. Just another quantum simulator (JAQSI) combines gate- and pulse-level simulation in one differentiable circuit model built upon JAX. Circuits are represented as pure functions of numerical inputs which support vectorised batches and JIT compilation. Within a single circuit, matrix-defined operations, gates synthesised from Hamiltonian time evolution and noise channels can be composed freely. For a fast simulation, gate and channel fusion reduces passes over the state, while adjoint differentiation computes expectation-value gradients with a constant number of statevectors. At pulse level, JAQSI reduces evolution under single-term Hamiltonians to a scalar pulse-area integral and reuses cached execution plans and compiled solvers. In a benchmark we compare JAQSI with PennyLane, Qiskit, Qibo, Qulacs, QuTiP and dynamiqs. At gate level, we observe performance either on par or an order of magnitude faster across statevector, density, noise and gradient simulation than the compared simulators up to 12 qubits. Beyond 18 qubits, JAQSI is on par with PennyLane Lightning in both statevector and gradient simulation. In the statevector and noisy density-matrix pulse benchmarks, it is at least 5 times faster than the other simulators, even with its closed-form solve disabled. Disabling the latter increases its runtime by at most a factor of 1.5. We provide JAQSI as open-source software on GitHub and PyPI.
Abstract Distributed quantum machine learning (QML) provides a natural framework for studying variational quantum models under distributed and feature-partitioned execution, but the accuracy-practicality trade-offs of vertical partitioning in the near-term regime remain insufficiently quantified. This work presents a controlled benchmark of a centralized hybrid reference model against vertically distributed QML architectures that split input features across two variational quantum circuits and combine the resulting low-dimensional measurement outputs either through a trainable dense layer or through parameter-free quantum-only aggregation rules. The models are evaluated on four binary-classification datasets under both gradient-based Adam and gradient-free ARO (asexual reproduction optimization). To assess hardware transfer, simulator-trained models are executed on IBM superconducting quantum processors using fixed-weight inference. Across all datasets, the centralized hybrid model achieves the highest mean accuracy, whereas the distributed variants require substantially fewer trainable parameters (24 or 31 versus 300), revealing a clear accuracy-capacity trade-off. The results further show that optimizer choice is particularly important for quantum-only aggregation rules. Hardware experiments yield accuracies broadly consistent with simulator re-evaluation, while stronger runtime resilience settings improve stability at the cost of increased execution time.
Training parameterized quantum circuits requires balancing optimization progress with limited evaluation budgets and the statistical uncertainty of near-term quantum hardware. We present a modular benchmarking framework that separates quantum search-direction estimation from classical parameter-update rules, allowing their interactions and sensitivities to be examined independently. We evaluate a suite of gradient-based, stochastic, and derivative-free optimizers across combinatorial optimization using the Quantum Approximate Optimization Algorithm (QAOA), supervised quantum machine learning using Iris classification and a quantum convolutional neural network (QCNN) for binary MNIST classification, and quantum chemistry using the variational quantum eigensolver (VQE) for molecular hydrogen. By separating objective evaluations from sample-circuit costs under finite-shot simulation and physical execution on a 156-qubit processor, we compare optimizer behavior across workloads with different parameter counts and measurement requirements. Four selected simulator and hardware case studies report terminal and best observed objectives separately, alongside post-training classifier accuracies. The comparisons include selected MaxCut and hydrogen trajectories and illustrate workload-dependent objective changes and evaluation costs, while the simulator benchmark compares both peak and mean performance across three seeds. The hardware runs do not establish an optimizer ranking or isolate a causal effect of device noise.
Among notable applications, quantum machine learning (QML) is a promising task that combines quantum computing with machine learning, cited for various types of complex computational problems. This chapter briefly summarizes the frameworks, software platforms, and toolchains currently available for implementing, simulating, and executing hybrid quantum–classical learning algorithms. Major frameworks (e.g., Qiskit Machine Learning, PennyLane, TensorFlow Quantum, and the PyTorch-based toolsets) are analyzed in detail based on their architectural design, functionality, and integration capabilities. They have several key features, such as variational quantum circuits, parameterized quantum gates, automatic differentiation capabilities, and easy integration into a classical deep learning ecosystem. The chapter groups together ongoing research in different architectural paradigms, practical usability aspects, and empirical performance tests. Additionally, it explores aspects of scalability, adaptability to hardware, noise resistance, and reproducibility. The results bring to light elements of the design of trade-offs for creating robust and efficient toolchains for QML, a QML best practice, and guidance for future QML design.