arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.04480quant-phcs.LGhep-ph
收藏

带缩放的量子绝热机器学习

Quantum adiabatic machine learning with zooming

California Institute of Technology(加州理工学院);DeepMind Technologies(深度思维科技公司);Lockheed Martin Advanced Technology Center(洛克希德·马丁先进技术中心);University of Southern California(南加州大学)

Alexander Zlokapa, Alex Mott, Joshua Job, Jean-Roch Vlimant, Daniel Lidar, Maria Spiropulu

摘要:

最近的工作表明,用于机器学习的量子退火(简称QAML)可以执行最先进的机器学习方法,具体应用于希格斯玻色子分类。我们提出了QAML-Z,一种新的算法,迭代放大的能量表面的一个区域,将问题映射到一个连续的空间,并依次应用量子退火的一组增强的弱分类器。在可编程量子退火机上的结果表明,QAML-Z在小训练集大小下与经典深度神经网络性能相匹配,在大训练集大小下将QAML和经典深度神经网络之间的性能裕度降低了近50%,如ROC曲线下面积所测量的。用于机器学习的量子退火算法的显着改进以及在连续优化问题上使用离散量子算法都开辟了一类可以通过量子退火器解决的新问题,并提出了近期量子机器学习对经典基准性能的方法。

英文摘要:

Recent work has shown that quantum annealing for machine learning, referred to as QAML, can perform comparably to state-of-the-art machine learning methods with a specific application to Higgs boson classification. We propose QAML-Z, a novel algorithm that iteratively zooms in on a region of the energy surface by mapping the problem to a continuous space and sequentially applying quantum annealing to an augmented set of weak classifiers. Results on a programmable quantum annealer show that QAML-Z matches classical deep neural network performance at small training set sizes and reduces the performance margin between QAML and classical deep neural networks by almost 50% at large training set sizes, as measured by area under the ROC curve. The significant improvement of quantum annealing algorithms for machine learning and the use of a discrete quantum algorithm on a continuous optimization problem both opens a new class of problems that can be solved by quantum annealers and suggests the approach in performance of near-term quantum machine learning towards classical benchmarks.

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。

↑