Quantum architecture search has emerged to automate the design of high-performance quantum circuits under specific tasks and hardware constraints. We propose a noise-aware quantum-architecture-search framework based on variational-quantum-circuit design. By incorporating a noise model into the training of parameterized quantum circuits, the proposed framework identifies the noise-robust architectures. We introduce a hybrid parameter-sharing $\varepsilon$-greedy strategy to optimize evaluation costs and circumvent local optima. Furthermore, an enhanced variable-depth nondominated sorting genetic algorithm is employed to navigate the vast search space, enabling an automated trade-off between architectural expressibility and quantum hardware overhead. The effectiveness of the framework is validated through quantum-machine-learning classification tasks and variational-quantum-eigensolver tasks under noisy conditions. Compared to existing approaches, our framework can search for quantum architectures with superior performance and greater resource efficiency under noisy conditions.

Close

PrevNext

View figure in article

• Quantum algorithms & computation
• Quantum circuits