arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.19147math.OCcs.LG
收藏

快速且有效的广义对称矩阵分解计算

Fast and Effective Computation of Generalized Symmetric Matrix Factorization

School of Computer Science and Engineering(计算机科学与工程学院);Guangdong Province Key Laboratory of Computational Science(广东省计算科学重点实验室);Sun Yat-sen University(中山大学);School of Mathematics and Information Science(数学与信息科学学院);Guangzhou University(广州大学);Department of Mathematics(数学系);The University of Tennessee, Knoxville(田纳西大学,诺克斯维尔)

Lei Yang, Han Wan, Min Zhang, Ling Liang

AI总结:

本文研究了一种非凸、非光滑、非利普希茨的广义对称矩阵分解模型,统一了机器学习、图像科学、工程等领域的广泛矩阵分解形式。提出了一种基于放松势函数的平均型非单调交替更新方法(A-NAUM),并证明了其全局收敛性及收敛速率。

摘要:

在本文中,我们研究了一种非凸、非光滑且非利普希茨的广义对称矩阵分解模型,该模型统一了出现在机器学习、图像科学、工程及相关领域中的广泛矩阵分解形式。我们首先建立了两个精确性属性。在建模方面,我们证明了一个精确惩罚属性,表明在合适条件下,对称诱导二次惩罚在惩罚参数足够大但有限时强制对称性,从而精确恢复相关的对称形式。在算法方面,我们引入了一个辅助变量分裂形式,并建立了精确松弛关系,严格地将原始目标函数的 stationary 点与松弛的潜在函数的 stationary 点联系起来。基于这些精确性属性,我们提出了一种基于松弛势函数的平均型非单调交替更新方法(A-NAUM)。在每次迭代中,A-NAUM 通过(近似)最小化势函数交替更新两个因子块,而辅助块通过闭式更新。为了确保收敛性和增强实际性能,我们进一步结合了平均型非单调线搜索,并证明其在温和条件下是良好定义的。此外,基于 Kurdyka-Łojasiewicz 性质及其相关的指数,我们建立了整个序列到 stationary 点的全局收敛性,并推导了收敛速率结果。最后,基于真实数据集的数值实验展示了 A-NAUM 的效率。

英文摘要:

In this paper, we study a nonconvex, nonsmooth, and non-Lipschitz generalized symmetric matrix factorization model that unifies a broad class of matrix factorization formulations arising in machine learning, image science, engineering, and related areas. We first establish two exactness properties. On the modeling side, we prove an exact penalty property showing that, under suitable conditions, the symmetry-inducing quadratic penalty enforces symmetry whenever the penalty parameter is sufficiently large but finite, thereby exactly recovering the associated symmetric formulation. On the algorithmic side, we introduce an auxiliary-variable splitting formulation and establish an exact relaxation relationship that rigorously links stationary points of the original objective function to those of a relaxed potential function. Building on these exactness properties, we propose an average-type nonmonotone alternating updating method (A-NAUM) based on the relaxed potential function. At each iteration, A-NAUM alternately updates the two factor blocks by (approximately) minimizing the potential function, while the auxiliary block is updated in closed form. To ensure the convergence and enhance practical performance, we further incorporate an average-type nonmonotone line search and show that it is well-defined under mild conditions. Moreover, based on the Kurdyka-Łojasiewicz property and its associated exponent, we establish global convergence of the entire sequence to a stationary point and derive convergence rate results. Finally, numerical experiments on real datasets demonstrate the efficiency of A-NAUM.

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。

↑