- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper is trying the address the problem that when QNNs deploy on quantum devices, due to intrinsic hardware noise, it suffer from severe performance degradation. The paper incorporates a flat minimum in DNNS into QNNs for quantum noise robustness. It proposes quantum sharpness-aware minimization (Q-SAM), which integrates the flat minima concept into the Riemannian quantum parameter space to seek minima that remain flat or invariant under quantum state perturbations induced by hardware noise. The proposed method was tested across image classification tasks with 4, 6, 8-quibit QNNs and validated on IBM quantum hardware.
Critical strengths
The paper is addressing an important practical problem, the geometry-aware optimization approach with theoretical motivation and evaluation across multiple noise models and different noise combinations evaluations on real quantum hardware.
Critical weaknesses
The experimental evaluation primarily limited to image classification benchmarks. However, the proposed Q-SAM aims to improve the robustness of quantum neural networks against hardware noise. It would be valuable to evaluate it’s generalizability beyond image classifications. Table 1 shows different types of noise which can be applied on single qubit, I wonder if these 5 types of noise and noise combinations cover all the noises. Could the author further clarify whether the simulations incorporate hardware-calibrated noise models?
Questions for authors
- Equation (4) Defined the optimization objective, which is QNN-loss deviation |L(˜ρ) − L(ρ)|, but I cannot find the definition of L(ρ). Please explain how to define this function and why it is defined in this way.
- The paper uses IBM Heron(133-qubit) hardware, but only evaluates 4, 6, 8 qubit QNNs, I think larger qubit experiments might be useful. As the nuber of qubits increase, there may be some noise accumulation.
- From line 359-365, the paper tries different number of qubit on different image classification datasets, how about the computational cost when increasing the number of qubit?
- Section 5.2 shows evaluation on both single-source noise and on composite noise, given that the paper aims to improve the robustness against quantum hardware noise, I wonder if the authors have done some testing on cross noise generalization, which means training on certain types of noises and testing on noises that not injected in training data.
3 comments
Q1. Definition of the QNN loss
Appendix A.2 already defines using the measurement in Eq. (31). For a circuit output state ,
Here, denotes the measured observables and applies the classical post-processing and cross-entropy loss for a fixed target label. Noise can change the measured values and, in turn, the classification loss. The quantity measures this change for the same input and label.
We added this definition immediately before Eq. (4).
Q2. Larger circuits and noise accumulation
Appendix D.2 already includes a 10-qubit experiment using amplitude encoding of inputs. Q-SAM achieves the highest noisy accuracy across all five channels, with gains of up to 11.40 percentage points over the strongest baseline.
| Optimizer | Nominal | Depolarizing | Amplitude damping | Phase damping | Bit flip | Phase flip |
|---|---|---|---|---|---|---|
| Adam | 90.92 | 47.88 | 49.56 | 88.83 | 41.38 | 88.34 |
| SAM | 91.12 | 52.34 | 52.82 | 88.31 | 46.50 | 88.03 |
| QNG | 90.32 | 52.06 | 53.14 | 88.27 | 52.02 | 88.83 |
| Q-SAM | 90.98 | 63.74 | 64.48 | 89.84 | 56.68 | 89.54 |
The 4–10-qubit simulations apply noise at successive circuit locations, so the reported accuracies reflect accumulated errors.
The theory also accounts for noise accumulation. In the weak local-noise regime, Eq. (20) in Appendix A.1 bounds the accumulated state displacement by . Under the revised coverage condition in Theorem 4.7, a clean circuit within reproduces the loss-relevant measurement outputs of the noisy state. The maximum loss variation over that region therefore bounds the noisy loss deviation.
We updated Section 5.1 to point directly to Appendix D.2 and Table 13.
Q3. Computational cost as qubit count increases
Appendix B already includes a computational-cost comparison for 4- and 6-qubit circuits (Table 7). We ran this comparison to assess how training cost grows with qubit count. Table 7 reports the number of circuit evaluations per optimizer update for Adam and Q-SAM.
| Configuration | Quantum parameters | Adam | Q-SAM |
|---|---|---|---|
| 4 qubits | 192 | 384 | 912 |
| 6 qubits | 432 | 864 | 2,040 |
| Increase | 2.25× | 2.25× | 2.24× |
Q-SAM’s evaluation count grows at nearly the same rate as Adam’s in this comparison. The block-diagonal QFIM approximation keeps metric construction linear in the parameter count for this architecture, and we amortize that cost by refreshing the metric every 20 updates. The cost of each circuit evaluation also grows with circuit size. For example, dense noisy simulation stores density-matrix entries for an -qubit circuit.
We expanded the cost discussion in Section 4.2.2 to point directly to the per-update quantum circuit evaluation counts in Appendix B (Table 7).
Q4. Cross-noise generalization
Our robustness experiments evaluate Q-SAM under noise conditions unseen during training. We train Q-SAM on noise-free circuits and introduce hardware noise only at evaluation. This applies to both the single-source and composite-noise experiments in Section 5.2.
Q-SAM optimizes toward quantum-native flat minima during noise-free training to reduce the sensitivity of the classification loss to hardware noise. In Section 5.3, Q-SAM achieves noisy accuracy close to that of noise-aware training (NAT) under the same composite noise (44.16% vs. 49.42%) and retains higher clean accuracy (76.50% vs. 50.52%). The practical benefit is that Q-SAM achieves this robustness without injecting noise or specifying a device-specific noise model during training.
We believe that this aspect makes Q-SAM naturally become a ‘cross-noise generalizable’ method rather than fitted to a certain type of noise pattern.
Follow-up on our response
Dear Reviewer 3eZh,
We appreciate your feedback on the experimental scope and your questions about scaling. With the discussion period ending soon, we wanted to follow up and see if there are any remaining questions or concerns we can address.
Following your suggestions to evaluate Q-SAM beyond image classification and on larger circuits, we added speech and text classification results and experiments with up to 10 qubits.
We thank the reviewer for their feedback. Below, we address robustness beyond image classification, hardware noise, and circuit scaling.
W1. Beyond image classification and hardware noise
Beyond image classification. We added two 10-class tasks, spoken command recognition on Speech Commands [1] and text emotion classification on GoEmotions [2]. Prior QNN studies address spoken commands [3] and text sentiment [4].
As in Table 2, we test each noise channel separately. Section 5.2 (Table 4) reports all four optimizers, with setup details in Appendix D.4 (Table 15). Perturbed test accuracies are averaged over five seeds. Parentheses show changes from nominal accuracy in percentage points.
Speech Commands. We used a 4-qubit data-reuploading circuit based on our MNIST architecture. Q-SAM improves mean noisy accuracy by 7.13 percentage points across the five channels while preserving nominal accuracy (78.15% vs. 77.95%).
GoEmotions. We used the 8-qubit circuit from our CIFAR-10 experiment. Q-SAM improves mean noisy accuracy by 14.65 percentage points, with a 3.14-point decrease in nominal accuracy.
Hardware noise. The five single-qubit channels in Table 1 are widely accepted as common hardware errors. The table below shows how these errors cover common erroneous physical cases:
Applying these local channels across qubits and layers allows multiple errors to occur in the same circuit and propagate through entangling gates. Qiskit Aer also combines gate, relaxation, and readout errors in its device noise models [5].
Composite noise and Heron calibration. Section 5.2 and Table 3 already include a composite-noise simulation to approximate IBM Heron errors. We apply gate depolarization, thermal relaxation, and readout error together during inference. McKay et al. [6, Appendix B] describe combining gate errors with relaxation over circuit time steps. The table below compares our settings with the corresponding ranges from IBM’s archived ibm_torino calibration data [7].
Table 3 uses representative noise strengths within these Heron calibration ranges.
In Table 3, Q-SAM achieved 44.16% vs. 29.66% for Adam under composite noise and 49.33% vs. 27.33% on the physical Heron processor.
References
[1] Warden. Speech Commands. 2018.
[2] Demszky et al. GoEmotions. ACL 2020.
[3] Qi and Tejedor. Classical-to-Quantum Transfer Learning for Spoken Command Recognition Based on Quantum Neural Networks. 2021.
[4] Liu et al. HCQNSC. EPJ Quantum Technology, 2026.
[5] Qiskit Aer. Device backend noise model simulations.
[6] McKay et al. Benchmarking Quantum Processor Performance at Scale.
[7] ibm_torino calibration snapshot (28 February 2024)