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 2405.00673quant-phmath-phmath.FAmath.MPmath.OA
收藏

矩阵几何均值的量子算法

Quantum algorithms for matrix geometric means

Nana Liu, Qisheng Wang, Mark M. Wilde, Zhicheng Zhang

AI总结:

本文提出矩阵几何均值的量子子程序,用于求解代数Riccati方程,并构建量子几何均值度量学习算法,应用于弱监督学习和异常检测,同时实现最优精度的保真度估计,并给出BQP完全问题。

摘要:

两个正定矩阵之间的矩阵几何均值可以从不同的角度定义——作为某些非线性方程组的解,作为黎曼几何中测地线上的点,以及作为某些优化问题的解。我们为矩阵几何均值设计了量子子程序,并构造了代数Riccati方程的解——这是一类重要的非线性方程组,出现在机器学习、最优控制、估计和滤波中。利用这些子程序,我们提出了一类新的量子学习算法,适用于经典和量子数据,称为量子几何均值度量学习,用于弱监督学习和异常检测。这些子程序还用于估计几何Rényi相对熵和Uhlmann保真度,特别是对于Uhlmann和Matsumoto保真度实现了对精度的最优依赖。最后,我们提供了一个基于矩阵几何均值的BQP完全问题,该问题可以通过我们的子程序求解。

英文摘要:

Matrix geometric means between two positive definite matrices can be defined from distinct perspectives - as solutions to certain nonlinear systems of equations, as points along geodesics in Riemannian geometry, and as solutions to certain optimisation problems. We devise quantum subroutines for the matrix geometric means, and construct solutions to the algebraic Riccati equation - an important class of nonlinear systems of equations appearing in machine learning, optimal control, estimation, and filtering. Using these subroutines, we present a new class of quantum learning algorithms, for both classical and quantum data, called quantum geometric mean metric learning, for weakly supervised learning and anomaly detection. The subroutines are also useful for estimating geometric Rényi relative entropies and the Uhlmann fidelity, in particular achieving optimal dependence on precision for the Uhlmann and Matsumoto fidelities. Finally, we provide a BQP-complete problem based on matrix geometric means that can be solved by our subroutines.

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。

↑