This paper presents a hardware-aware AutoML framework for quantum–classical architectures that jointly optimizes predictive quality, hardware feasibility, and robustness under realistic device noise. Across 700 proposals, the full pipeline evaluated 252 candidates versus 520 for an unconstrained baseline, reducing wall-clock search time from 31.4 hours to 17.9 hours and yielding 43.0 percent compute savings under matched shot budgets. The resulting Pareto set improved median hardware cost proxy from 0.62 to 0.48 while maintaining comparable validation loss, and the top-10 architecture overlap with full evaluation remained 0.80, indicating stable selection fidelity under budgeted training. Under calibrated noise increases, the selected hardware-aware model exhibited macro-F1 degradation of 0.041 compared with 0.093 for a baseline deep selection, and cross-backend performance retention reached 94.2 percent versus 87.6 percent across three backends with heterogeneous coherence and connectivity profiles. Deployment feasibility improved materially, with median inference latency decreasing from 412 ms to 268 ms and mean failure rate dropping from 2.1 percent to 0.8 percent over 10,000 repeated executions per backend. On three benchmarks at 1,024 to 1,536 shots per update, hardware-aware selections achieved macro-F1 between 0.821 and 0.854 while reducing expected calibration error from 0.061 to 0.039 on average. These results show that explicit hardware constraints and noise sensitivity signals enable faster discovery of deployable architectures with stronger robustness and reliability properties.
This paper presents a hardware-aware AutoML framework for quantum–classical architectures that jointly optimizes predictive quality, hardware feasibility, and robustness under realistic device noise. Across 700 proposals, the full pipeline evaluated 252 candidates versus 520 for an unconstrained baseline, reducing wall-clock search time from 31.4 hours to 17.9 hours and yielding 43.0 percent compute savings under matched shot budgets. The resulting Pareto set improved median hardware cost proxy from 0.62 to 0.48 while maintaining comparable validation loss, and the top-10 architecture overlap with full evaluation remained 0.80, indicating stable selection fidelity under budgeted training. Under calibrated noise increases, the selected hardware-aware model exhibited macro-F1 degradation of 0.041 compared with 0.093 for a baseline deep selection, and cross-backend performance retention reached 94.2 percent versus 87.6 percent across three backends with heterogeneous coherence and connectivity profiles. Deployment feasibility improved materially, with median inference latency decreasing from 412 ms to 268 ms and mean failure rate dropping from 2.1 percent to 0.8 percent over 10,000 repeated executions per backend. On three benchmarks at 1,024 to 1,536 shots per update, hardware-aware selections achieved macro-F1 between 0.821 and 0.854 while reducing expected calibration error from 0.061 to 0.039 on average. These results show that explicit hardware constraints and noise sensitivity signals enable faster discovery of deployable architectures with stronger robustness and reliability properties.
uantum computing offers the potential to solve selected computational problems more efficiently than classical systems by leveraging quantum mechanical principles such as superposition and entanglement. However, current quantum devices operate in the noisy intermediatescale quantum (NISQ) regime, where limited coherence times, gate errors, measurement instability, and hardware variability significantly constrain practical performance. As a result, many quantum machine learning architectures that appear promising under idealized simulation conditions experience substantial degradation when executed under realistic noisy environments. This thesis investigates the problem of robustness in hybrid quantum neural network (HQNN) systems operating under realistic NISQ conditions. Rather than focusing primarily on quantum expressivity or claims of quantum advantage, the work examines whether practical hybrid quantum learning can maintain stable optimization and reliable inference in the presence of stochastic perturbations. A robustness-engineering framework is developed that integrates learned-readout decoding, multi-observable quantum feature extraction, architecture-level optimization, stability-aware training, and noise-augmented learning within a unified hybrid quantum-classical pipeline. To evaluate the framework, a comprehensive benchmarking methodology is developed across multiple datasets, architectures, perturbation environments, software frameworks, and hardware platforms. The experiments compare classical machine learning models, quantum kernel methods, and several HQNN architectures, including quanvolutional neural networks, quantum convolutional neural networks, and quantum transfer learning systems. Performance is evaluated under both noiseless and noisy conditions using standardized metrics, cross-noise validation, architecture-level comparisons, and real IBM Quantum hardware execution. The results demonstrate that baseline HQNN systems are highly sensitive to optimization instability, parity-based information loss, measurement variability, and perturbation accumulation. The experiments further reveal that robustness, rather than representational expressivity alone, is the dominant factor limiting practical hybrid quantum learning under realistic NISQ conditions. Through successive robustness-engineering stages, noisy performance improves from approximately 0.37 to 0.50 in baseline architectures to approximately 0.97 under several benchmark environments while maintaining substantially improved stability and reduced degradation under perturbation. These findings establish robustness as a central design objective for practical quantum machine learning. The thesis demonstrates that reliable hybrid quantum learning emerges through coordinated interaction between quantum feature generation, adaptive classical inference, stability-aware optimization, and hardware-aware architecture design. More broadly, the results suggest that hybrid quantum-AI systems are most effective when viewed as integrated quantum-classical computational frameworks in which quantum circuits function as probabilistic feature generators operating within larger robustness-oriented learning pipelines.
Noisy Intermediate-Scale Quantum (NISQ) devices are constrained by short coherence times and imperfect control, limiting the practical performance of near-term quantum algorithms. While Quantum Architecture Search (QAS) automates circuit design using reinforcement learning, most existing approaches optimize architectures under ideal or fixed average-case noise models. As a result, the discovered circuits often exhibit poor robustness when deployed on realistic hardware subject to noise variability. In this paper, we propose a coevolutionary framework for noise-resistant quantum architecture search. A circuit-designing agent, referred to as the Architect, is trained against an adaptive Hardware-Aware Saboteur (HAS). The HAS models worst-case, yet physically plausible, operating conditions by amplifying backend-derived noise components under a constrained noise amplification budget. The Architect is implemented as a Proximal Policy Optimization agent with a discrete gate alphabet, while the HAS is a separate reinforcement learning agent that selects budget-constrained amplification over single-qubit, two-qubit, and measurement noise channels. Their interaction is mediated by an adversarial environment that stabilizes training via an annealed mixture of nominal and stress-tested performance and a curriculum over the amplification budget. The framework is evaluated on Greenberger–Horne–Zeilinger (GHZ) state preparation for three to five qubits and on small variational quantum eigensolver benchmarks. Compared to a reinforcement learning-based QAS baseline and a hardware-efficient ansatz baseline, the coevolutionary Architect achieves significantly improved robustness under backend-aligned noise amplification and demonstrates stronger generalization to unseen noise families. These results indicate that explicitly training against adaptive, hardware-aligned worst-case noise is an effective strategy for discovering noise-resilient quantum circuits suitable for NISQ-era execution.
Hybrid quantum-classical neural networks (HQNNs) integrate quantum circuits with classical layers, each operating under fundamentally different computational paradigms, which makes hardware resource estimation challenging. The training of quantum circuits on real devices requires thousands of circuit executions, which is impractical on current NISQ devices. Therefore, most HQNNs are evaluated on classical simulators, with hardware cost approximated using floating-point operations (FLOPs). However, FLOPs and existing quantum resource estimation methods (e.g., gate counts) overlook key quantum hardware-specific factors such as gate durations, limited qubit connectivity, and noise, all of which ultimately determine the true cost and scalability of quantum circuits.
In this paper, we propose an analytical quantum cost model that estimates quantum hardware resources using real backend calibration data, incorporating gate durations, routing overheads, and noise-induced sampling inefficiencies. To complement this, we develop a classical cost model that converts FLOPs into device-specific throughput, enabling a unified time-based representation of hardware resource cost for both subsystems of HQNNs. Building on these analytical models, we present Hyb-HANAS, a hardware-aware hybrid neural architecture search framework, which jointly optimizes accuracy, hardware cost, and parameter count using NSGA-II. Hyb-HANAS identifies Pareto-optimal trade-offs and cross-domain co-adaptation between classical and quantum components of HQNNs. Beyond NAS, the proposed analytical quantum cost model is broadly applicable to quantum hardware benchmarking, compiler evaluation, and training-time estimation of quantum circuits on NISQ devices.
Quantum machine learning (QML) systems executed on noisy intermediate-scale quantum (NISQ) hardware are vulnerable to both adversarial perturbations and backend-dependent noise effects. Existing robustness evaluations are typically performed under fixed execution conditions and rarely consider deployment shift between training and inference backends. This work proposes a threat-model–driven benchmark framework for evaluating QML robustness under adversarial attacks, stochastic device noise, and backend-dependent deployment variability. Using FGSM and PGD attacks, we analyze robustness scaling under varying training budgets, encoding strategies, and fake quantum backends. Experimental results demonstrate substantial backend-dependent robustness variability and reduced robustness transfer across heterogeneous backend environments. The findings highlight the importance of backend-aware robustness evaluation for realistic NISQ-era QML deployments.
Designing quantum neural networks (QNNs) that are both accurate and deployable on NISQ hardware is challenging. Handcrafted ansatze must balance expressivity, trainability, and resource use, while limited qubits often necessitate circuit cutting. Existing quantum architecture search methods primarily optimize accuracy while only heuristically controlling quantum and mostly ignore the exponential overhead of circuit cutting. We introduce QNAS, a neural architecture search framework that unifies hardware aware evaluation, multi objective optimization, and cutting overhead awareness for hybrid quantum classical neural networks (HQNNs). QNAS trains a shared parameter SuperCircuit and uses NSGA-II to optimize three objectives jointly: (i) validation error, (ii) a runtime cost proxy measuring wall clock evaluation time, and (iii) the estimated number of subcircuits under a target qubit budget. QNAS evaluates candidate HQNNs under a few epochs of training and discovers clear Pareto fronts that reveal tradeoffs between accuracy, efficiency, and cutting overhead. Across MNIST, Fashion-MNIST, and Iris benchmarks, we observe that embedding type and CNOT mode selection significantly impact both accuracy and efficiency, with angle-y embedding and sparse entangling patterns outperforming other configurations on image datasets, and amplitude embedding excelling on tabular data (Iris). On MNIST, the best architecture achieves 97.16% test accuracy with a compact 8 qubit, 2 layer circuit; on the more challenging Fashion-MNIST, 87.38% with a 5 qubit, 2 layer circuit; and on Iris, 100% validation accuracy with a 4 qubit, 2 layer circuit. QNAS surfaces these design insights automatically during search, guiding practitioners toward architectures that balance accuracy, resource efficiency, and practical deployability on current hardware.
Discovering effective parameterized quantum circuits (PQCs) remains a major obstacle in the noisy intermediatescale quantum (NISQ) era due to barren plateaus, noise sensitivity, and heavy trial-and-error in ansatz selection and initialization. We propose Q-Transfer-Search, a transferable agentic AI framework that unifies meta-learning and automated machine learning (AutoML) to accelerate quantum algorithm discovery. Our method learns reusable parameter priors via meta-learning, enabling fast adaptation to new tasks, while a noise-aware architecture controller proposes PQCs optimized for hardware constraints. A measurement-efficient evaluator based on classical shadows and parameter-shift rules provides low-cost feedback for both inner and outer optimization loops. Evaluations on VQE, QAOA, and quantum machine learning tasks show that Q-Transfer-Search achieves lower energy errors, higher approximation ratios, and improved classification accuracy while reducing circuit evaluations and measurement shots. Compared to state-of-the-art baselines such as QuantumNAS, Meta-VQA, Q-MAML, and MG-Net, our framework consistently improves convergence speed and robustness. These results highlight the promise of agentic AI in enabling scalable, transferable, and resource-efficient quantum algorithm design.