Author(s) :

Albert Aslan Yelken.

Volume/Issue :

Abstract :

Quantum computing hardware is prone to decoherence and control errors, which can reduce entanglement and lead to mixed states. Practical quantum algorithms must extract insights from this noisy data. We test the hypothesis that a compact, circuit-based Quantum Generative Adversarial Network (QGAN) trained against a moving, noise-scheduled target can learn the action of a depolarizing channel and generate a family of noisy entangled two-qubit states that match state-level similarity and reproduce entanglement trends. We implement a compact QGAN in PennyLane with TensorFlow and train it against a moving target formed by Bell-pair states passed through a depolarizing channel whose strength is scheduled during training. The generator and discriminator are variational circuits; learning is assessed by state-level similarity (fidelity and trace distance) and by entanglement measures (concurrence and negativity). Our model learns the action of the noise channel and reproduces a family of noisy, entangled two-qubit states. Our results indicate that QGANs can capture hardware-relevant noise while preserving essential structure in the data. Such models can serve as error-aware state preparers, compact surrogates for device noise, and practical tools for quantum data augmentation and benchmarking on near-term quantum computing hardware. To our knowledge, this is the first systematic QGAN evaluation combining dynamic depolarizing noise schedule, finite-shot/readout-noisy training, and entanglement-aware metrics.