Ciliberto Carlo, Herbster Mark, Ialongo Alessandro Davide, Pontil Massimiliano, Rocchetto Andrea, Severini Simone, Wossnig Leonard
Department of Computer Science, University College London, London, UK.
Department of Engineering, University of Cambridge, Cambridge, UK.
Proc Math Phys Eng Sci. 2018 Jan;474(2209):20170551. doi: 10.1098/rspa.2017.0551. Epub 2018 Jan 17.
Recently, increased computational power and data availability, as well as algorithmic advances, have led machine learning (ML) techniques to impressive results in regression, classification, data generation and reinforcement learning tasks. Despite these successes, the proximity to the physical limits of chip fabrication alongside the increasing size of datasets is motivating a growing number of researchers to explore the possibility of harnessing the power of quantum computation to speed up classical ML algorithms. Here we review the literature in quantum ML and discuss perspectives for a mixed readership of classical ML and quantum computation experts. Particular emphasis will be placed on clarifying the limitations of quantum algorithms, how they compare with their best classical counterparts and why quantum resources are expected to provide advantages for learning problems. Learning in the presence of noise and certain computationally hard problems in ML are identified as promising directions for the field. Practical questions, such as how to upload classical data into quantum form, will also be addressed.
最近，计算能力的提升、数据可用性的增加以及算法的进步，使得机器学习（ML）技术在回归、分类、数据生成和强化学习任务中取得了令人瞩目的成果。尽管取得了这些成功，但随着芯片制造接近物理极限以及数据集规模不断增大，越来越多的研究人员开始探索利用量子计算的能力来加速经典ML算法的可能性。在此，我们回顾量子机器学习领域的文献，并为经典机器学习和量子计算领域的混合读者群体探讨相关观点。我们将特别强调阐明量子算法的局限性、它们与最佳经典算法相比的情况，以及为何量子资源有望在学习问题上提供优势。在噪声环境下的学习以及机器学习中某些计算困难的问题被确定为该领域有前景的发展方向。诸如如何将经典数据上传为量子形式等实际问题也将得到探讨。
