Merged amplitude encoding for Chebyshev quantum Kolmogorov-Arnold networks

arXiv:2603.02818v4 Announce Type: replace Abstract: Quantum Kolmogorov--Arnold networks evaluate each edge activation function as a quantum inner product, creating a trade-off between qubit count and the number of circuit executions per forward pass. We introduce merged amplitude encoding for the Chebyshev-edge classical-to-classical QKAN (CCQKAN), which packs the element-wise products of all $n$ input-edge vectors of an output node into a single amplitude state, reducing circuit executions by a factor of $n$ while using no more qubits than the sequential SWAP-test baseline once its measurement registers are counted. The merged and original circuits compute the same quantity exactly; we characterize what this consolidation costs in trainability. Across 10 network configurations and 16 random seeds, the two circuits are indistinguishable under ideal conditions. Under finite-shot training with a hardware-standard SPSA optimizer at matched measurement budget, the merged circuit incurs a small systematic loss deficit that grows with network width (significant in 6 of 10 configurations), consistent with amplified estimator noise in the merged state; under depolarizing noise no systematic difference is detected. A parameter-matched single-qubit data re-uploading baseline reaches substantially higher loss on the same tasks while using fewer qubits and executions, delineating complementary resource regimes. No quantum advantage is claimed.

Abstract:Quantum Kolmogorov--Arnold networks evaluate each edge activation function as a quantum inner product, creating a trade-off between qubit count and the number of circuit executions per forward pass. We introduce merged amplitude encoding for the Chebyshev-edge classical-to-classical QKAN (CCQKAN), which packs the element-wise products of all $n$ input-edge vectors of an output node into a single amplitude state, reducing circuit executions by a factor of $n$ while using no more qubits than the sequential SWAP-test baseline once its measurement registers are counted. The merged and original circuits compute the same quantity exactly; we characterize what this consolidation costs in trainability. Across 10 network configurations and 16 random seeds, the two circuits are indistinguishable under ideal conditions. Under finite-shot training with a hardware-standard SPSA optimizer at matched measurement budget, the merged circuit incurs a small systematic loss deficit that grows with network width (significant in 6 of 10 configurations), consistent with amplified estimator noise in the merged state; under depolarizing noise no systematic difference is detected. A parameter-matched single-qubit data re-uploading baseline reaches substantially higher loss on the same tasks while using fewer qubits and executions, delineating complementary resource regimes. No quantum advantage is claimed.

arXiv:2603.02818 [quant-ph]

(or arXiv:2603.02818v4 [quant-ph] for this version)

https://doi.org/10.48550/arXiv.2603.02818 Focus to learn more arXiv-issued DOI via DataCite

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.

aiqbench analysis

Merged amplitude encoding for Chebyshev quantum Kolmogorov-Arnold networks

Related coverage