We present a systematic investigation of deep learning methods applied to quantum error mitigation of noisy output probability distributions from measured quantum circuits. We compare different architectures, from fully connected neural networks to transformers, and we test different design/training modalities, identifying sequence-to-sequence, attention-based models as the most effective on our datasets. These models consistently produce mitigated distributions that are closer to the ideal outputs when tested on both simulated and real device data obtained from IBM superconducting quantum processing units (QPU) up to five qubits. Across several different circuit depths, our approach outperforms other baseline error mitigation techniques. We perform a series of ablation studies to examine: how different input features (circuit, device properties, noisy output statistics) affect performance; cross-dataset generalization across circuit families; and transfer learning to a different IBM QPU. We observe that generalization performance across similar devices with the same architecture works effectively, without needing to fully retrain models.

翻译：本文系统研究了深度学习在量子误差缓解中的应用，针对从测量量子电路中获取的含噪输出概率分布。我们比较了从全连接神经网络到Transformer的不同架构，并测试了多种设计/训练模式，发现基于注意力机制的序列到序列模型在我们的数据集上最为有效。在模拟数据和从IBM超导量子处理单元（QPU）获取的真实设备数据（最多五量子比特）上进行测试时，这些模型持续产生更接近理想输出的缓解后分布。在多种不同电路深度下，我们的方法优于其他基线误差缓解技术。我们进行了一系列消融研究，以考察：不同输入特征（电路、设备属性、含噪输出统计量）如何影响性能；跨电路家族的跨数据集泛化能力；以及向不同IBM QPU的迁移学习。我们观察到，在具有相同架构的相似设备间，泛化性能表现良好，无需对模型进行完全重新训练。