Prototype-Guided Optimization of Quantum Data Embeddings with Linear Cost
Abstract
In supervised quantum machine learning with classical data, classification performance critically depends on the geometry induced by quantum data embedding. Existing data-adaptive approaches rely on pairwise fidelity evaluations between samples, which scale as O(B2) for B samples and create a computational bottleneck in iterative embedding optimization. To address this issue, we propose a prototype-guided framework for efficient data-adaptive quantum embedding. Using class-prototype separation and sample-to-prototype compactness, we derive a measurable lower certificate for class-ensemble distinguishability and construct a prototype-based objective requiring only O(B) fidelity evaluations. We integrate this objective into an end-to-end pipeline that combines task-specific quantum circuit architecture optimization with continuous refinement of the data-embedding parameters. Across five benchmark datasets with up to 20 qubits, our method retains competitive quantum kernel support vector machine (SVM) performance while reducing fidelity-evaluation cost, with particularly strong gains over budget-matched pairwise optimization on T-MNIST. Geometric analyses examine how the learned embeddings relate to kernel alignment and classification margins, revealing dataset-dependent benefits and limitations. We further derive a prototype-based classifier in the reproducing kernel Hilbert space that provides an explicit witness for the SVM objective and a low-cost proxy for model selection, and extend the framework to multiple prototypes for multimodal class structures.
Related
- Error-Corrected Quantum Optimization via Rydberg Atom Array Embeddings
- Sampled-Based Guided Quantum Walk: Non-variational quantum algorithm for combinatorial optimization
- Quantum-Assisted Optimization Guided by Machine-Learned Risk Maps for Aerial Surveillance Routing
- Symmetry-guided algorithms for variational quantum optimization
- Efficient Fourier-Based Linear Combination of Unitaries and Applications in Quantum Optimization
BibTeX
@misc{jeong2026prototypeguided,
title = {{Prototype-Guided Optimization of Quantum Data Embeddings with Linear Cost}},
author = {Seokhoon Jeong and Daniel K. Park},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.24403},
eprint = {2610.24403},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.24403},
}
RIS
TY - UNPB
TI - Prototype-Guided Optimization of Quantum Data Embeddings with Linear Cost
AU - Seokhoon Jeong
AU - Daniel K. Park
PY - 2026
DA - 2026/10/17
PB - arXiv
DO - 10.48550/arxiv.2610.24403
UR - https://arxiv.org/abs/2610.24403
AB - In supervised quantum machine learning with classical data, classification performance critically depends on the geometry induced by quantum data embedding. Existing data-adaptive approaches rely on pairwise fidelity evaluations between samples, which scale as O(B^2) for B samples and create a computational bottleneck in iterative embedding optimization. To address this issue, we propose a prototype-guided framework for efficient data-adaptive quantum embedding. Using class-prototype separation and sample-to-prototype compactness, we derive a measurable lower certificate for class-ensemble distinguishability and construct a prototype-based objective requiring only O(B) fidelity evaluations. We integrate this objective into an end-to-end pipeline that combines task-specific quantum circuit architecture optimization with continuous refinement of the data-embedding parameters. Across five benchmark datasets with up to 20 qubits, our method retains competitive quantum kernel support vector machine (SVM) performance while reducing fidelity-evaluation cost, with particularly strong gains over budget-matched pairwise optimization on T-MNIST. Geometric analyses examine how the learned embeddings relate to kernel alignment and classification margins, revealing dataset-dependent benefits and limitations. We further derive a prototype-based classifier in the reproducing kernel Hilbert space that provides an explicit witness for the SVM objective and a low-cost proxy for model selection, and extend the framework to multiple prototypes for multimodal class structures.
ER -