Deep Learning Approaches to Quantum Error Mitigation
This work addresses error mitigation in quantum computing, which is crucial for improving the reliability of quantum algorithms, but it is incremental as it builds on existing deep learning methods applied to a specific domain.
The paper tackled quantum error mitigation for noisy quantum circuits by comparing deep learning architectures, finding that attention-based models produced mitigated distributions closer to ideal outputs on simulated and real device data up to five qubits, outperforming other baseline techniques across various circuit depths.
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.