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 2104.13348math.OC
收藏

一般低秩矩阵恢复问题的局部和全局线性收敛

Local and Global Linear Convergence of General Low-rank Matrix Recovery Problems

Yingjie Bi, Haixiang Zhang, Javad Lavaei

摘要:

在约束等距性质的假设下,研究了基于梯度的局部搜索法在对称和非对称两种情形下求解一般目标的低秩矩阵恢复问题的收敛速度.首先,我们开发了一种新的技术来验证Polyak-Lojasiewicz不等式的全局极小,这导致了一个局部的线性收敛区域的梯度下降法的附近。其次,基于局部收敛结果和本文证明的一个严格鞍点性质,给出了扰动梯度下降法全局线性收敛的两个新条件.发展的局部和整体收敛结果提供了更强的理论保证比现有的结果。作为一个副产品,这项工作显着提高了现有的RIP常数的界限,以保证不存在虚假的解决方案。

英文摘要:

We study the convergence rate of gradient-based local search methods for solving low-rank matrix recovery problems with general objectives in both symmetric and asymmetric cases, under the assumption of the restricted isometry property. First, we develop a new technique to verify the Polyak-Lojasiewicz inequality in a neighborhood of the global minimizers, which leads to a local linear convergence region for the gradient descent method. Second, based on the local convergence result and a sharp strict saddle property proven in this paper, we present two new conditions that guarantee the global linear convergence of the perturbed gradient descent method. The developed local and global convergence results provide much stronger theoretical guarantees than the existing results. As a by-product, this work significantly improves the existing bounds on the RIP constant required to guarantee the non-existence of spurious solutions.

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。

↑