arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.03388quant-phcs.LG
收藏

用囚禁离子实现量子非参数学习的协议

Protocol for implementing quantum nonparametric learning with trapped ions

South China Normal University（华南师范大学）；Nanjing University（南京大学）；The University of Hong Kong（香港大学）

Dan-Bo Zhang, Shi-Liang Zhu, Z. D. Wang

备注：
5 pages. Close to published version
发表信息：
Phys. Rev. Lett. 124, 010506 (2020)
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

摘要：

非参数学习能够通过从一组新的输入数据和所有样本之间的相似性中提取信息来进行可靠的预测。在这里，我们指出了一个量子范式的非参数学习，它提供了一个指数加速的样本大小。通过将数据编码到量子特征空间中，将数据之间的相似性定义为量子态的内积。引入一个量子训练态，将所有样本数据叠加在一起，将相关信息编码在其二分纠缠谱中进行学习。利用量子矩阵工具箱，我们证明了通过纠缠谱变换可以得到一个用于预测的训练态。我们进一步设计了一个可行的方案来实现囚禁离子的量子非参数学习，并展示了量子叠加在机器学习中的强大功能。

英文摘要：

Nonparametric learning is able to make reliable predictions by extracting information from similarities between a new set of input data and all samples. Here we point out a quantum paradigm of nonparametric learning which offers an exponential speedup over the sample size. By encoding data into quantum feature space, similarity between the data is defined as an inner product of quantum states. A quantum training state is introduced to superpose all data of samples, encoding relevant information for learning in its bipartite entanglement spectrum. We demonstrate that a trained state for prediction can be obtained by entanglement spectrum transformation, using quantum matrix toolbox. We further work out a feasible protocol to implement the quantum nonparametric learning with trapped ions, and demonstrate the power of quantum superposition for machine learning.

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。

↑