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 1906.08902cs.LGcs.CCquant-phstat.ML
收藏

量子支持向量机

Quantum-Inspired Support Vector Machine

University of Science and Technology of China(中国科学技术大学);CAS Centre for Excellence and Synergetic Innovation Centre in Quantum Information and Quantum Physics(中国科学院量子信息与量子科技创新卓越中心);University of Oxford(牛津大学);Hefei National Laboratory for Physical Sciences at Microscale(合肥微尺度物质科学国家实验室)

Chen Ding, Tian-Yi Bao, He-Liang Huang

摘要:

支持向量机(Support Vector Machine,SVM)是一种功能强大且灵活的监督学习模型,它可以对数据进行分类和回归分析,通常的算法复杂度与数据空间的维数和数据点的数量呈多项式关系。为了解决大数据问题,提出了一种量子支持向量机算法,该算法能够实现最小二乘支持向量机(LS-SVM)的指数加速比。在这里,受量子SVM算法的启发,我们提出了一个量子启发的经典算法LS-SVM。在我们的方法中,一种改进的快速采样技术,即间接采样,提出了采样的核矩阵和分类。我们首先考虑线性核的LS-SVM,然后讨论我们的方法推广到非线性核。理论分析表明,对于低秩、低条件数和高维数据矩阵,该算法可以在数据空间维数和数据点数均为对数的运行时间内以任意的成功概率进行分类,与量子SVM的运行时间相匹配。

英文摘要:

Support vector machine (SVM) is a particularly powerful and flexible supervised learning model that analyzes data for both classification and regression, whose usual algorithm complexity scales polynomially with the dimension of data space and the number of data points. To tackle the big data challenge, a quantum SVM algorithm was proposed, which is claimed to achieve exponential speedup for least squares SVM (LS-SVM). Here, inspired by the quantum SVM algorithm, we present a quantum-inspired classical algorithm for LS-SVM. In our approach, a improved fast sampling technique, namely indirect sampling, is proposed for sampling the kernel matrix and classifying. We first consider the LS-SVM with a linear kernel, and then discuss the generalization of our method to non-linear kernels. Theoretical analysis shows our algorithm can make classification with arbitrary success probability in logarithmic runtime of both the dimension of data space and the number of data points for low rank, low condition number and high dimensional data matrix, matching the runtime of the quantum SVM.

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。

↑