arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1602.04799quant-phcs.LGstat.ML
收藏

量子感知器模型

Quantum Perceptron Models

Microsoft Research(微软研究院)

Nathan Wiebe, Ashish Kapoor, Krysta M Svore

摘要:

我们展示了量子计算如何在感知器模型的计算和统计复杂性方面提供非平凡的改进。我们开发了两个量子算法的感知器学习。第一种算法利用量子信息处理来确定分离超平面,其使用在数据点$N$的数量中次线性的多个步骤,即$O(\sqrt{N})$。第二个算法说明了如何通过量子手段将$O(\frac{1}{γ^2})$的经典错误界进一步改进为$O(\frac{1}{\sqrtγ})$,其中$γ$表示裕度。这种改进是通过将量子振幅放大应用于感知器模型的版本空间解释来实现的。

英文摘要:

We demonstrate how quantum computation can provide non-trivial improvements in the computational and statistical complexity of the perceptron model. We develop two quantum algorithms for perceptron learning. The first algorithm exploits quantum information processing to determine a separating hyperplane using a number of steps sublinear in the number of data points $N$, namely $O(\sqrt{N})$. The second algorithm illustrates how the classical mistake bound of $O(\frac{1}{γ^2})$ can be further improved to $O(\frac{1}{\sqrtγ})$ through quantum means, where $γ$ denotes the margin. Such improvements are achieved through the application of quantum amplitude amplification to the version space interpretation of the perceptron model.

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。

↑