aiqbench analysis
JGRA introduces a framework that assesses robustness in quantum neural networks by leveraging Jacobian geometry to link clean-regime structures with noisy inference behaviors. This approach addresses a critical gap in NISQ-era quantum machine learning by providing geometric descriptors that predict model resilience to unseen noise through entropy-matched calibration and noise-conditioned extraction. The work offers a practical pathway for evaluating QNN reliability under realistic decoherence constraints, bridging classical robustness principles with quantum-specific challenges.
JGRA: Jacobian Geometry Robustness Assessment in NISQ Noise-Aware Quantum Neural Networks
arXiv:2606.09964v1 Announce Type: cross Abstract: The NISQ era places stringent constraints on quantum computation, where noise and decoherence fundamentally limit performance. In classical deep learning, model robustness and resilience to perturbations are well studied: deep neural networks (DNNs) maintain high performance despite pruning, noise injection, and structural perturbations due to inherent redundancy in their representations. A central challenge in quantum machine learning is to transfer this notion of robustness to quantum neural networks (QNNs) under realistic NISQ noise. While classical deep learning exhibits robustness through structural redundancy, analogous principles for QNNs remain underdeveloped. We propose JGRA: a framework for assessing robustness in noise-aware QNNs via Jacobian geometry, capturing model sensitivity to parameter perturbations induced by noise. Our method includes entropy-matched noise calibration, noise-aware training, and noise-conditioned Jacobian extraction, yielding geometric descriptors that link clean-regime structure to noisy inference behaviour. We also empirically demonstrate that these descriptors encode predictive information about robustness under unseen noise.
Abstract:The NISQ era places stringent constraints on quantum computation, where noise and decoherence fundamentally limit performance. In classical deep learning, model robustness and resilience to perturbations are well studied: deep neural networks (DNNs) maintain high performance despite pruning, noise injection, and structural perturbations due to inherent redundancy in their representations. A central challenge in quantum machine learning is to transfer this notion of robustness to quantum neural networks (QNNs) under realistic NISQ noise. While classical deep learning exhibits robustness through structural redundancy, analogous principles for QNNs remain underdeveloped. We propose JGRA: a framework for assessing robustness in noise-aware QNNs via Jacobian geometry, capturing model sensitivity to parameter perturbations induced by noise. Our method includes entropy-matched noise calibration, noise-aware training, and noise-conditioned Jacobian extraction, yielding geometric descriptors that link clean-regime structure to noisy inference behaviour. We also empirically demonstrate that these descriptors encode predictive information about robustness under unseen noise.
Accepted at IEEE qCCL 2026. Author accepted manuscript. 6 pages
Quantum Physics (quant-ph); Machine Learning (cs.LG)
arXiv:2606.09964 [quant-ph]
(or arXiv:2606.09964v1 [quant-ph] for this version)
https://doi.org/10.48550/arXiv.2606.09964 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 256 words
Related coverage
JGRA: Jacobian Geometry Robustness Assessment in NISQ Noise-Aware Quantum Neural Networks
arXiv · Jun 12, 2026
PIRAMID: Progress and Plans
LessWrong · Jul 27, 2026
Source-preserving alignment for robust evidence localization in scientific PDFS
arXiv · Sep 29, 2026
News
Quantum Computing Report · Jun 7, 2026