arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.01938quant-phcs.LG
收藏

数据在量子机器学习中的力量

Power of data in quantum machine learning

Google Research(谷歌研究院);Institute for Quantum Information and Matter, Caltech(加州理工学院量子信息与物质研究所)

Hsin-Yuan Huang, Michael Broughton, Masoud Mohseni, Ryan Babbush, Sergio Boixo, Hartmut Neven, Jarrod R. McClean

摘要:

将量子计算用于机器学习是量子技术最令人兴奋的潜在应用之一。然而,提供数据的机器学习任务可能与通常研究的计算任务有很大不同。在这项工作中,我们证明了一些经典的难以计算的问题可以通过经典的机器从数据中学习来轻松预测。使用严格的预测误差界为基础,我们开发了一种方法来评估潜在的量子优势在学习任务。边界是紧密的渐近和经验预测广泛的学习模型。这些构造解释了数值结果,表明在数据的帮助下,经典机器学习模型可以与量子模型竞争,即使它们是针对量子问题定制的。然后,我们提出了一个投影量子模型,提供了一个简单而严格的量子加速学习问题的容错制度。对于近期实现,我们在工程数据集上展示了与一些经典模型相比的显着预测优势,这些工程数据集旨在展示迄今为止基于门的量子机器学习的最大数值测试之一中的最大量子优势,高达30个量子位。

英文摘要:

The use of quantum computing for machine learning is among the most exciting prospective applications of quantum technologies. However, machine learning tasks where data is provided can be considerably different than commonly studied computational tasks. In this work, we show that some problems that are classically hard to compute can be easily predicted by classical machines learning from data. Using rigorous prediction error bounds as a foundation, we develop a methodology for assessing potential quantum advantage in learning tasks. The bounds are tight asymptotically and empirically predictive for a wide range of learning models. These constructions explain numerical results showing that with the help of data, classical machine learning models can be competitive with quantum models even if they are tailored to quantum problems. We then propose a projected quantum model that provides a simple and rigorous quantum speed-up for a learning problem in the fault-tolerant regime. For near-term implementations, we demonstrate a significant prediction advantage over some classical models on engineered data sets designed to demonstrate a maximal quantum advantage in one of the largest numerical tests for gate-based quantum machine learning to date, up to 30 qubits.

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。

↑