arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.17895quant-ph
收藏

在量子希尔伯特空间中利用矩阵积态进行几何原型学习

Geometric Prototype Learning in Quantum Hilbert Space with Matrix Product States

Capital Normal University(首都师范大学);Department of Cardiac Arrhythmia, State Key Laboratory of Cardiovascular Disease, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College(中国医学科学院北京协和医学院国家心血管病中心阜外医院心血管疾病国家重点实验室心律失常科)

Kun Zhang, Lei Ding, Sheng-Chen Bai, Jing Sun, An-Qi Jing, Min Tang, Shi-Ju Ran

AI总结:

本文提出了一种在量子希尔伯特空间中基于原型的学习方法,利用生成矩阵积态作为类代表,并通过量子态的几何度量进行分类和聚类等任务,展示了在Fashion-MNIST和真实心电图数据集上的优越性能。

摘要:

量子概率提供了一个新的框架,用于在希尔伯特空间中制定机器学习(ML)问题。我们介绍了一种基于原型的学习方案,其中类代表被编码为生成矩阵积态(MPS)。由于这些原型与量子编码的数据样本处于同一个希尔伯特空间中,可以通过量子态的几何度量执行各种ML任务,如分类和聚类。这种方法将原型学习从经典特征空间提升到量子希尔伯特空间。在Fashion-MNIST和一个现实世界的心电图数据集上的基准测试表明,我们的方法在超越经典原型方法的同时,仍与标准黑箱神经网络具有竞争力。我们还识别出由量子概率原型引起的“吸引力”效应,并引入基于原型距离的降维方案。我们的结果确立了量子态作为可解释的原型学习框架,为在量子希尔伯特空间中设计ML算法开辟了新方向。

英文摘要:

Quantum probability provides a novel framework for formulating machine-learning (ML) problems in Hilbert space. We introduce a prototype-based learning scheme where class representatives are encoded as generative matrix product states (MPS). Because these prototypes reside in the same Hilbert space as quantum-encoded data samples, various ML tasks such as classification and clustering can be performed through geometric measures of quantum states. This approach lifts prototype learning from classical feature space to quantum Hilbert space. Benchmarks on Fashion-MNIST and a real-world electrocardiogram dataset demonstrate that our method outperforms classical prototype approaches while remaining competitive with standard black-box neural networks. We also identify an ``attraction'' effect induced by the quantum-probabilistic prototypes and introduce a dimensionality-reduction scheme based on prototype distances. Our results establish quantum states as an explainable framework for prototype learning, opening new directions for designing ML algorithms in quantum Hilbert space.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑