[论文解读] Machine learning \& artificial intelligence in the quantum domain

Vedran Dunjko, Hans J. Briegel|arXiv (Cornell University)|Sep 8, 2017

Quantum Computing Algorithms and Architecture被引用 12

一句话总结

本综述探讨了量子信息处理（QIP）与机器学习（ML）/人工智能（AI）之间的协同交叉，展示了量子计算如何通过提升样本复杂度和计算复杂度的效率来加速ML任务，同时ML技术也增强了量子实验设计与控制。研究强调了在学习效率、数据处理和自主量子研究方面存在的量子优势，将ML/AI定位为量子技术的潜在‘杀手级应用’。

ABSTRACT

Quantum information technologies, and intelligent learning systems, are both emergent technologies that will likely have a transforming impact on our society. The respective underlying fields of research -- quantum information (QI) versus machine learning (ML) and artificial intelligence (AI) -- have their own specific challenges, which have hitherto been investigated largely independently. However, in a growing body of recent work, researchers have been probing the question to what extent these fields can learn and benefit from each other. QML explores the interaction between quantum computing and ML, investigating how results and techniques from one field can be used to solve the problems of the other. Recently, we have witnessed breakthroughs in both directions of influence. For instance, quantum computing is finding a vital application in providing speed-ups in ML, critical in our "big data" world. Conversely, ML already permeates cutting-edge technologies, and may become instrumental in advanced quantum technologies. Aside from quantum speed-up in data analysis, or classical ML optimization used in quantum experiments, quantum enhancements have also been demonstrated for interactive learning, highlighting the potential of quantum-enhanced learning agents. Finally, works exploring the use of AI for the very design of quantum experiments, and for performing parts of genuine research autonomously, have reported their first successes. Beyond the topics of mutual enhancement, researchers have also broached the fundamental issue of quantum generalizations of ML/AI concepts. This deals with questions of the very meaning of learning and intelligence in a world that is described by quantum mechanics. In this review, we describe the main ideas, recent developments, and progress in a broad spectrum of research investigating machine learning and artificial intelligence in the quantum domain.

研究动机与目标

• 调查量子信息处理（QIP）与机器学习（ML）/人工智能（AI）之间的相互益处，特别是两领域如何相互促进。
• 识别并分析ML任务中关键的量子优势，如降低样本复杂度和提升运行时间效率。
• 研究ML和AI在设计、优化和自主执行量子实验中的作用。
• 探讨在完全量子世界中，学习与智能概念的量子推广所引发的基础性问题。
• 评估量子增强ML的实际可行性与理论极限，包括抗噪声能力与实现约束。

提出的方法

• 综述量子机器学习（QML）在理论与实验方面的进展，包括监督学习与强化学习的量子加速。
• 分析用于哈密顿量估计、相位估计以及使用量子增强采样的广义量子态学习的量子算法。
• 将经典ML模型（如神经网络和支持向量机）应用于量子数据与量子控制任务。
• 引入量子增强架构，如量化霍普菲尔德网络与振幅编码学习模型，以提升学习容量。
• 开发量子智能体-环境框架用于强化学习，实现在交互环境中的量子增强决策。
• 通过计算学习理论评估量子优势，包括量子PAC学习与查询复杂度降低的成员查询模型。

实验结果

研究问题

• RQ1 量子计算在多大程度上能为机器学习问题提供样本复杂度与运行时间的加速？
• RQ2 机器学习技术如何用于自主设计、优化与控制量子实验？
• RQ3 量子增强学习的理论极限是什么？与经典方法相比有何差异？
• RQ4 学习与AI概念的量子推广能否催生量子世界中新的智能框架？
• RQ5 哪些实际限制（如噪声、数据结构与资源需求）制约了量子ML算法的实现？

主要发现

• 量子机器学习在样本复杂度方面提供了理论加速，特定条件下量子PAC学习可实现相对于经典方法的指数级改进。
• 用于哈密顿量估计与相位估计的量子增强算法相比经典方法展现出更高的精度与更低的资源需求。
• 振幅编码与量化霍普菲尔德网络通过利用叠加与纠缠实现更高的学习容量。
• 量子强化学习智能体在交互式学习任务中展现出性能提升潜力，理论上的查询效率具有优势。
• 机器学习已用于自动化量子实验设计与控制，减少了人为干预并提升了实验结果。
• 尽管理论前景广阔，但大多数量子ML方案仍受限于实际挑战，如高条件数、对噪声的敏感性以及缺乏可扩展的量子硬件。