aiqbench analysis
This study demonstrates that sparsified Kolmogorov-Arnold Networks (KANs) can provide structural interpretability in quantum state tomography by aligning internal pathways with known Pauli groupings rather than merely achieving regression accuracy. The approach successfully isolates relevant measurement subsets under noise and finite-shot conditions, offering a verifiable framework for auditing learned reconstruction rules against physical constraints. For tech audiences, this highlights a shift toward models where internal architecture explicitly mirrors domain-specific physics, enabling more trustworthy and explainable quantum machine learning systems.
Sparsified Kolmogorov-Arnold Networks for Interpretable Quantum State Tomography
arXiv:2606.11814v1 Announce Type: cross Abstract: Machine-learning approaches to quantum state tomography can achieve high reconstruction fidelity, but the physical structure used by the trained model often remains implicit. Here we ask whether a sparsified Kolmogorov-Arnold Network (KAN) can be used not only as a regressor, but also as an inspectable reconstruction rule whose internal organization can be checked against known Pauli structure. We study a controlled three-qubit GHZ-family benchmark in which all 63 non-identity Pauli expectation values are used to reconstruct three GHZ-subspace variables: the population imbalance $z$, the real off-diagonal component $c$, and the imaginary off-diagonal component $s$. Under finite-shot sampling and depolarizing noise, external ablation identifies the extended 12-channel GHZ-relevant Pauli set from the 63 measurements, with exact top-12 recovery across the tested shot counts and depolarizing-noise strengths. These support patterns remain stable across multi-seed random-initialization and noise-level analyses, and collapse under random-label controls. The dominant pruned input-hidden-output pathways organize Z-type population observables and X/Y off-diagonal observables in a pattern consistent with the analytic GHZ Pauli grouping, and sparse formula recovery recovers the canonical signed Pauli relations. The contribution of the KAN is therefore pathway-level structural interpretability within a neural reconstruction model, rather than superior sparse regression. Together with negative controls, these probes provide a consistency chain for auditing learned reconstruction rules against known physical structure.
Abstract:Machine-learning approaches to quantum state tomography can achieve high reconstruction fidelity, but the physical structure used by the trained model often remains implicit. Here we ask whether a sparsified Kolmogorov-Arnold Network (KAN) can be used not only as a regressor, but also as an inspectable reconstruction rule whose internal organization can be checked against known Pauli structure. We study a controlled three-qubit GHZ-family benchmark in which all 63 non-identity Pauli expectation values are used to reconstruct three GHZ-subspace variables: the population imbalance $z$, the real off-diagonal component $c$, and the imaginary off-diagonal component $s$. Under finite-shot sampling and depolarizing noise, external ablation identifies the extended 12-channel GHZ-relevant Pauli set from the 63 measurements, with exact top-12 recovery across the tested shot counts and depolarizing-noise strengths. These support patterns remain stable across multi-seed random-initialization and noise-level analyses, and collapse under random-label controls. The dominant pruned input-hidden-output pathways organize Z-type population observables and X/Y off-diagonal observables in a pattern consistent with the analytic GHZ Pauli grouping, and sparse formula recovery recovers the canonical signed Pauli relations. The contribution of the KAN is therefore pathway-level structural interpretability within a neural reconstruction model, rather than superior sparse regression. Together with negative controls, these probes provide a consistency chain for auditing learned reconstruction rules against known physical structure.
Quantum Physics (quant-ph); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2606.11814 [quant-ph]
(or arXiv:2606.11814v1 [quant-ph] for this version)
https://doi.org/10.48550/arXiv.2606.11814 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 · 313 words
Related coverage
Low-Rank Kolmogorov-Arnold Generator Flows for Interpretable Operator Learning
arXiv · Oct 12, 2026
New method automatically finds errors in quantum states
Quantum Zeitgeist · Sep 7, 2026
Efficient Representation of multicategorical local Hilbert spaces: nonlinear Restricted Boltzmann Machines to Kolmogorov-Arnold Networks
arXiv · Sep 9, 2026
Merged amplitude encoding for Chebyshev quantum Kolmogorov-Arnold networks
arXiv · Oct 9, 2026