Sharp Target-Domain Certificates for Quantum-Kernel Advantage under Distribution Shift
Abstract
Quantum predictive advantage under shift usually requires known target labels. We derive the assumption-free sharp identified interval for the finite-batch advantage of a fixed candidate over the best member of a prespecified fixed classical-kernel family under any bounded loss and unrestricted completions of the unaudited labels; zero-one accuracy has exact closed-form partial-label updates. Across eight security shifts, zero-label upper endpoints against 115 classical kernels span 0.002-0.088. Retrospective auditing reduces every endpoint to 0.010 with 0-33 of 500 labels, including entangling-ZZ models. Prospective corroboration on two eligible tasks met predefined criteria: four task-classifier medians require 0-3 labels (overall median 0; maximum 76), and all 20 realized effects are negative; a third task fails its feature gate. Protocol controls reverse an apparent advantage, while finite-shot noise can increase predictive distinctness without useful advantage. The framework separates protocol validity, target predictive indispensability, and quantum relevance.
Related
- Exponential advantage in continuous-variable quantum state learning
- Quantum metrological advantage of high-order squeezed states
- A Framework for Quantum Advantage
- Constant-round quantum advantage in communication complexity for total functions
- Asymptotic advantage of quantum one-way and SMP communication for total functions
BibTeX
@misc{fernandezbarrios2026sharp,
title = {{Sharp Target-Domain Certificates for Quantum-Kernel Advantage under Distribution Shift}},
author = {Roberto Fernández-Barrios and Iker Pastor-López and Asier González-Santocildes and Pablo García Bringas},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.00080},
eprint = {2610.00080},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.00080},
}
RIS
TY - UNPB
TI - Sharp Target-Domain Certificates for Quantum-Kernel Advantage under Distribution Shift
AU - Roberto Fernández-Barrios
AU - Iker Pastor-López
AU - Asier González-Santocildes
AU - Pablo García Bringas
PY - 2026
DA - 2026/10/01
PB - arXiv
DO - 10.48550/arxiv.2610.00080
UR - https://arxiv.org/abs/2610.00080
AB - Quantum predictive advantage under shift usually requires known target labels. We derive the assumption-free sharp identified interval for the finite-batch advantage of a fixed candidate over the best member of a prespecified fixed classical-kernel family under any bounded loss and unrestricted completions of the unaudited labels; zero-one accuracy has exact closed-form partial-label updates. Across eight security shifts, zero-label upper endpoints against 115 classical kernels span 0.002-0.088. Retrospective auditing reduces every endpoint to 0.010 with 0-33 of 500 labels, including entangling-ZZ models. Prospective corroboration on two eligible tasks met predefined criteria: four task-classifier medians require 0-3 labels (overall median 0; maximum 76), and all 20 realized effects are negative; a third task fails its feature gate. Protocol controls reverse an apparent advantage, while finite-shot noise can increase predictive distinctness without useful advantage. The framework separates protocol validity, target predictive indispensability, and quantum relevance.
ER -