[论文解读] Quantum Machine Learning: from physics to software engineering

Alexey Melnikov, Mohammad Kordzanganeh+2 more|arXiv (Cornell University)|Jan 4, 2023

Quantum Computing Algorithms and Architecture被引用 8

一句话总结

本评审综述量子技术如何提升机器学习，聚焦混合量子-经典模型、数据编码、训练与理论基础，特别是在 NISQ 约束下。

ABSTRACT

Quantum machine learning is a rapidly growing field at the intersection of quantum technology and artificial intelligence. This review provides a two-fold overview of several key approaches that can offer advancements in both the development of quantum technologies and the power of artificial intelligence. Among these approaches are quantum-enhanced algorithms, which apply quantum software engineering to classical information processing to improve keystone machine learning solutions. In this context, we explore the capability of hybrid quantum-classical neural networks to improve model generalization and increase accuracy while reducing computational resources. We also illustrate how machine learning can be used both to mitigate the effects of errors on presently available noisy intermediate-scale quantum devices, and to understand quantum advantage via an automatic study of quantum walk processes on graphs. In addition, we review how quantum hardware can be enhanced by applying machine learning to fundamental and applied physics problems as well as quantum tomography and photonics. We aim to demonstrate how concepts in physics can be translated into practical engineering of machine learning solutions using quantum software.

研究动机与目标

• 解释量子技术如何增强经典机器学习以提高效率和可扩展性。
• 综述量子神经网络、数据编码策略与用于 NISQ 时代应用的变分线路。
• 讨论量子机器学习中的学习理论、泛化与贝叶斯视角。
• 强调无论是在错误缓解、断层成像还是自动化实验等量子硬件任务中，ML如何提供帮助。

提出的方法

• 对机器学习范式（无监督、监督、强化学习）进行分类，并讨论量子方法如何加速或改进它们。
• 详细描述将数据编码到量子设备的策略（态嵌入、振幅嵌入、观测量嵌入）及其对表达能力的影响。
• 回顾参数化量子线路（PQC）及硬件高效、TTN/MPS、QCNN等QNN架构的选择。
• 解释QNN的梯度计算方法（参数移位规则、伴随方法、基于黎曼/几何的途径）及诸如荒凉板等问题。
• 讨论量子学习理论的联系（核方法、贝叶斯QNN、泛化界限）以及QNN作为傅里叶估计器的普适性。
• 描述混合量子-经典神经网络及其在 NISQ 硬件上的潜在优势。

Figure 1: Interdisciplinary paradigm of quantum machine learning that is based on current classical information, quantum technologies, and artificial intelligence, respectively (the details are given in the text).

实验结果

研究问题

• RQ1 如何利用量子技术加速或增强经典机器学习任务？
• RQ2 量子模型的有效数据编码策略有哪些，它们如何影响模型表达性？
• RQ3 在真实量子硬件上，哪些训练策略与梯度计算方法对QNNs可行？
• RQ4 量子机器学习如何解决硬件挑战（错误缓解、断层成像）并通过量子行走等过程揭示量子优势？

主要发现

• 量子神经网络提供一个框架，其中参数在经典方式下更新，而量子线路提供特征嵌入与评估。
• 数据编码的选择（态、振幅、观测量）对模型表达性和性能具有决定性影响。
• 梯度方法如参数移位规则实现了与量子处理单元的训练兼容性，然而由于参数数量庞大，扩展性仍是挑战。
• 荒凉板问题在深度或高度纠缠的量子线路中带来可训练性挑战，需要通过架构与初始化策略来维持可训练性。
• 对监督型QML的核方法式解释将QNN与经典核方法联系起来，启示潜在优势与训练动态。
• 混合量子-经典架构在利用量子优势的同时缓解 NISQ 时代局限方面展现出希望。

Figure 2: Timeline with milestones of quantum machine learning achievements.