aiqbench analysis
This paper introduces AeRot, a quantum kernel architecture that leverages specific circuit structures to capture inductive biases missing in classical tuned kernels for chaotic systems like Lorenz-63. By fusing amplitude encoding with grouped single-qubit rotations, the method demonstrates measurable advantage over standard RBF and Matern kernels specifically within unstable saddle-approach regimes where classical Euclidean kernels fail to resolve trajectory ambiguity. The study provides a mechanistic localization of quantum kernel utility without claiming computational separation, offering a concrete architectural solution for forecasting chaotic dynamics.
Structured Quantum Kernels for Chaotic Forecasting
arXiv:2609.13360v1 Announce Type: new Abstract: Quantum kernels promise exponentially large feature spaces, but expressive circuits render their Gram matrices uninformative, bandwidth tuning collapses them toward classical RBF, and the practical consensus is that quantum kernels add nothing on classical data. We answer another productive question, an architectural one: whether the structure of an encoding circuit can carry an inductive bias that tuned classical kernels lack. We introduce AeRot, a quantum kernel fusing amplitude encoding of l2-normalized delay windows with a grouped single-qubit rotation layer that assigns contiguous temporal blocks to each qubit, making the circuit delay-window-aware. On Lorenz-63 kernel ridge regression with cross-validated bandwidths over 100 seeds, AeRot outperforms tuned RBF and Matern-5/2, the advantage emerging at physical horizons >= 0.15 tu and reaching +0.137 mean R^2 at 0.25 tu (5 qubits, window 32). Linear-stability analysis of the window tail localises the advantage to the unstable saddle-approach regime: AeRot wins 83% of windows in the most unstable decile, with the win rate rising monotonically with tail instability and a sign flip at the local stability boundary. The difficulty is fold-branch ambiguity: trajectories approaching the saddle are locally diverging, and Euclidean kernels struggle to resolve which lobe the trajectory will commit to. Structural diagnostics confirm Gram matrices structurally distinct from tuned RBF, with strictly higher target-kernel alignment at every horizon. The gain is architectural: a finite-sample inductive-bias effect of temporally structured encoding on a folded attractor, with no computational-separation claim attached. To our knowledge this is the first mechanistic localisation of quantum-kernel advantage to a specific dynamical regime of a classical system.
Abstract:Quantum kernels promise exponentially large feature spaces, but expressive circuits render their Gram matrices uninformative, bandwidth tuning collapses them toward classical RBF, and the practical consensus is that quantum kernels add nothing on classical data. We answer another productive question, an architectural one: whether the structure of an encoding circuit can carry an inductive bias that tuned classical kernels lack. We introduce AeRot, a quantum kernel fusing amplitude encoding of l2-normalized delay windows with a grouped single-qubit rotation layer that assigns contiguous temporal blocks to each qubit, making the circuit delay-window-aware. On Lorenz-63 kernel ridge regression with cross-validated bandwidths over 100 seeds, AeRot outperforms tuned RBF and Matern-5/2, the advantage emerging at physical horizons >= 0.15 tu and reaching +0.137 mean R^2 at 0.25 tu (5 qubits, window 32). Linear-stability analysis of the window tail localises the advantage to the unstable saddle-approach regime: AeRot wins 83% of windows in the most unstable decile, with the win rate rising monotonically with tail instability and a sign flip at the local stability boundary. The difficulty is fold-branch ambiguity: trajectories approaching the saddle are locally diverging, and Euclidean kernels struggle to resolve which lobe the trajectory will commit to. Structural diagnostics confirm Gram matrices structurally distinct from tuned RBF, with strictly higher target-kernel alignment at every horizon. The gain is architectural: a finite-sample inductive-bias effect of temporally structured encoding on a folded attractor, with no computational-separation claim attached. To our knowledge this is the first mechanistic localisation of quantum-kernel advantage to a specific dynamical regime of a classical system.
arXiv:2609.13360 [quant-ph]
(or arXiv:2609.13360v1 [quant-ph] for this version)
https://doi.org/10.48550/arXiv.2609.13360 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 · 347 words
Related coverage
WISER and E.ON Advance Energy Demand Forecasting with Quantum Machine Learning
The Quantum Insider · Jul 24, 2026
Chaotic quantum system learns data with simple controls
Quantum Zeitgeist · Oct 13, 2026
Empirical Characterization of Learning Geometry in Hybrid Quantum Forecasting Models
arXiv · Aug 21, 2026
LiQSS: Post-Transformer Linear Quantum-Inspired State-Space Tensor Networks for Real-Time 6G
arXiv · Jun 8, 2026