arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.02802math.OCcs.ITmath.IT
收藏

仿射秩最小化问题的随机方差约化梯度

Stochastic Variance Reduced Gradient for affine rank minimization problem

Ningning Han, Juan Nie, Jian Lu, Michael K. Ng

摘要:

本文提出了一种有效的随机方差降低梯度下降算法来解决仿射秩最小化问题,该问题包括从线性测量中找到一个最小秩的矩阵。该算法作为一种随机梯度下降策略,比全梯度算法具有更好的复杂度。它还减小了每次迭代时随机梯度的方差,加快了收敛的收敛速率。在约束等距条件下,我们证明了该算法线性收敛于期望解。数值实验表明,与现有的贪婪算法相比,该算法在效率、自适应性和精确度之间具有明显的优势.

英文摘要:

We develop an efficient stochastic variance reduced gradient descent algorithm to solve the affine rank minimization problem consists of finding a matrix of minimum rank from linear measurements. The proposed algorithm as a stochastic gradient descent strategy enjoys a more favorable complexity than full gradients. It also reduces the variance of the stochastic gradient at each iteration and accelerate the rate of convergence. We prove that the proposed algorithm converges linearly in expectation to the solution under a restricted isometry condition. The numerical experiments show that the proposed algorithm has a clearly advantageous balance of efficiency, adaptivity, and accuracy compared with other state-of-the-art greedy algorithms.

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。

↑