分布偏移下量子核优势的尖锐目标域证书
Sharp Target-Domain Certificates for Quantum-Kernel Advantage under Distribution Shift
浏览论文内容
中文总结 AI 辅助
本文提出无假设尖锐识别区间，量化分布偏移下量子核优势，通过回顾性审计和前瞻性验证，区分协议有效性、目标预测不可或缺性与量子相关性。
中文摘要 AI 辅助
在分布偏移下，量子预测优势通常需要已知的目标标签。我们推导了在任意有界损失和未审计标签的无限制补全下，固定候选相对于预指定固定经典核族中最佳成员在有限批次优势上的无假设尖锐识别区间；零一准确率具有精确的闭式部分标签更新。在八种安全偏移中，针对115个经典核的零标签上端点跨度在0.002至0.088之间。回顾性审计将每个端点降至0.010，使用500个标签中的0至33个，包括纠缠ZZ模型。对两个合格任务的前瞻性验证满足预定标准：四个任务分类器中位数需要0至3个标签（总体中位数0；最大76），所有20个实现效应均为负；第三个任务未通过其特征门控。协议控制逆转了表面上的优势，而有限射击噪声可以增加预测区分度而不产生有用优势。该框架区分了协议有效性、目标预测不可或缺性和量子相关性。
英文摘要
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.
发表机构
- Faculty of Engineering, University of Deusto（德乌斯托大学工程学院）
机构由 AI 辅助整理，请以论文原文为准。
