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 1809.02773math.NAcs.NA
收藏

通过最优采样复杂度的黎曼优化求解相位less方程组

Solving systems of phaseless equations via Riemannian optimization with optimal sampling complexity

Hong Kong University of Science and Technology(香港科技大学);Fudan University(复旦大学)

Jian-Feng Cai, Ke Wei

AI总结:

本文提出基于秩1正定矩阵嵌入流形的黎曼梯度下降算法及其截断变体,证明截断变体在方程数量与未知数数量成比例时能有效恢复解,且在理论和实验上均优于其他非凸优化方法。

摘要:

本文提出了一种黎曼梯度下降算法及其截断变体,用于求解相位less方程组$|Ax|^2=y$。算法基于问题内在的低秩结构,利用秩1正定矩阵的嵌入流形进行开发。理论分析证明,截断变体在方程数量与未知数数量成比例时能够实现有效恢复。分析中的两个关键成分是关联截断线性算子的受限良好条件性和受限弱相关性。实验评估显示,本文算法在理论保证和实际性能上均优于其他最先进的非凸一阶方法。

英文摘要:

A Riemannian gradient descent algorithm and a truncated variant are presented to solve systems of phaseless equations $|Ax|^2=y$. The algorithms are developed by exploiting the inherent low rank structure of the problem based on the embedded manifold of rank-$1$ positive semidefinite matrices. Theoretical recovery guarantee has been established for the truncated variant, showing that the algorithm is able to achieve successful recovery when the number of equations is proportional to the number of unknowns. Two key ingredients in the analysis are the restricted well conditioned property and the restricted weak correlation property of the associated truncated linear operator. Empirical evaluations show that our algorithms are competitive with other state-of-the-art first order nonconvex approaches with provable guarantees.

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。

↑