量子分类器通过幅度编码实现高维特征稳定学习，兼顾准确与安全。
SAFE Quantum Machine Learning with Variational Quantum Classifiers
- 用可学习的古典预编码层结合归一化幅度嵌入，提升模型稳定性。
- 在多个数据集上性能媲美经典模型，且对噪声和特征移除更鲁棒。
- 适合安全关键场景，如医疗或自动驾驶中的可信机器学习。
我们提出一种变分量子分类器，通过幅度编码在高维深层表示上运行，并由可学习的古典预编码层稳定。结合归一化的幅度嵌入与有界量子可观测量，该模型生成结构化且平滑的假设类，对输入变化敏感度可控。模型可靠性通过基于Cramer-von Mises散度的SAFE-AI指标评估，实现准确率、鲁棒性和可解释性维度的一致衡量。实验表明，所提量子模型在预测性能上与强基线经典模型相当，同时展现出更均衡的SAFE可靠性表现，对噪声更具鲁棒性，在结构化特征移除下也更稳定。这些结果表明，变分量子电路为安全关键场景下的面向稳定的SAFE学习提供了原则性机制。
原文摘要 · Abstract (English)
We propose a variational quantum classifier operating on high dimensional deep representations via amplitude encoding, stabilized by a learnable classical pre encoding layer.By combining normalized amplitude embeddings with bounded quantum observables, the resulting model induces a structured and smooth hypothesis class with controlled sensitivity to input variations. Model reliability is assessed using SAFE-AI metrics derived from the Cramer von Mises divergence, enabling consistent evaluation across accuracy, robustness, and explainability dimensions. Empirical results show that the proposed quantum model provides competitive predictive performance compared with strong classical baselines while exhibiting a more balanced SAFE reliability profile, with improved robustness to noise and stability under structured feature removal. These findings suggest that variational quantum circuits offer a principled mechanism for stability oriented SAFE learning in safety critical settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。