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 2301.02601quant-phcs.LG
收藏

SEQUENT:利用序列量子增强训练实现可追溯的量子机器学习

SEQUENT: Towards Traceable Quantum Machine Learning using Sequential Quantum Enhanced Training

LMU Munich(慕尼黑大学);SAP SE(SAP公司)

Philipp Altmann, Leo Sünkel, Jonas Stein, Tobias Müller, Christoph Roch, Claudia Linnhoff-Popien

AI总结:

针对混合量子-经典机器学习中经典与量子影响无法严格分离的问题,提出 SEQUENT 序列量子增强训练架构与流程,并通过形式化论证和初步实验验证其可追溯性与适用性。

摘要:

将量子计算等新计算范式应用于机器学习领域近来受到关注。然而,由于利用纯量子硬件解决高维现实应用尚不可行,因此已有研究提出了同时使用经典和量子机器学习范式的混合方法。例如,迁移学习方法已被证明能够成功应用于混合图像分类任务。尽管如此,有益的电路架构仍有待探索。因此,追踪所选电路架构和参数化的影响,对于开发可有益应用的混合方法至关重要。然而,当前方法包含对两部分同时进行训练的过程,因而无法严格区分经典部分与量子部分的影响。因此,这些架构可能产生这样的模型:在取得优越预测准确率的同时,只使用尽可能少的量子影响。为解决这一问题,我们提出了 Sequential Quantum Enhanced Training(SEQUENT,序列量子增强训练),这是一种改进的架构和训练流程,用于将量子计算方法可追溯地应用于混合机器学习。此外,我们为当前方法的缺陷提供了形式化证据,并给出初步实验结果,作为 SEQUENT 适用性的概念验证。

英文摘要:

Applying new computing paradigms like quantum computing to the field of machine learning has recently gained attention. However, as high-dimensional real-world applications are not yet feasible to be solved using purely quantum hardware, hybrid methods using both classical and quantum machine learning paradigms have been proposed. For instance, transfer learning methods have been shown to be successfully applicable to hybrid image classification tasks. Nevertheless, beneficial circuit architectures still need to be explored. Therefore, tracing the impact of the chosen circuit architecture and parameterization is crucial for the development of beneficially applicable hybrid methods. However, current methods include processes where both parts are trained concurrently, therefore not allowing for a strict separability of classical and quantum impact. Thus, those architectures might produce models that yield a superior prediction accuracy whilst employing the least possible quantum impact. To tackle this issue, we propose Sequential Quantum Enhanced Training (SEQUENT) an improved architecture and training process for the traceable application of quantum computing methods to hybrid machine learning. Furthermore, we provide formal evidence for the disadvantage of current methods and preliminary experimental results as a proof-of-concept for the applicability of SEQUENT.

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。

↑