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 2112.08449quant-ph
收藏

用于离线量子增强机器学习的核矩阵完成

Kernel Matrix Completion for Offline Quantum-Enhanced Machine Learning

Annie Naveh, Imogen Fitzgerald, Anna Phan, Andrew Lockwood, Travis L. Scholten

摘要:

通过量子核增强经典机器学习算法是量子机器学习领域一个快速发展的研究课题。使用内核(包括经典内核和量子内核)的一个关键挑战是ML工作流涉及获取新的观察结果,需要计算新的内核值。在生成新观测的地方和量子计算机之间来回传输数据会产生时间延迟;这种延迟可能会超过首先使用QML算法的时间尺度。在这项工作中,我们表明量子核矩阵可以扩展到使用经典的(弦图为基础的)矩阵完成算法,将新的数据。完美完成所需的最小样本复杂度取决于矩阵秩。我们的经验表明,(a)量子核矩阵可以使用该算法完成时,满足最小的样本复杂性,(b)完成的错误优雅地降低在有限采样噪声的存在下,和(c)量子核矩阵的秩弱依赖于生成内核的量子特征映射的可表达性。此外,在现实世界中,工业相关的数据集,即使没有达到最小的样本复杂度,完成错误也会表现得很好。

英文摘要:

Enhancing classical machine learning (ML) algorithms through quantum kernels is a rapidly growing research topic in quantum machine learning (QML). A key challenge in using kernels -- both classical and quantum -- is that ML workflows involve acquiring new observations, for which new kernel values need to be calculated. Transferring data back-and-forth between where the new observations are generated & a quantum computer incurs a time delay; this delay may exceed the timescales relevant for using the QML algorithm in the first place. In this work, we show quantum kernel matrices can be extended to incorporate new data using a classical (chordal-graph-based) matrix completion algorithm. The minimal sample complexity needed for perfect completion is dependent on matrix rank. We empirically show that (a) quantum kernel matrices can be completed using this algorithm when the minimal sample complexity is met, (b) the error of the completion degrades gracefully in the presence of finite-sampling noise, and (c) the rank of quantum kernel matrices depends weakly on the expressibility of the quantum feature map generating the kernel. Further, on a real-world, industrially-relevant data set, the completion error behaves gracefully even when the minimal sample complexity is not reached.

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。

↑