arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.02356math.OCcs.CVcs.LGeess.SPstat.ML
收藏

对偶主成分追踪和正交字典学习的流形邻近点法

Manifold Proximal Point Algorithms for Dual Principal Component Pursuit and Orthogonal Dictionary Learning

Texas A&M University(德克萨斯A&M大学);Cainiao Network(菜鸟网络);University of California, Davis(加州大学戴维斯分校);The Chinese University of Hong Kong(香港中文大学)

Shixiang Chen, Zengde Deng, Shiqian Ma, Anthony Man-Cho So

摘要:

我们考虑的问题,最大化的线性映射的$\ell_1$范数的球,这出现在各种机器学习应用,如正交字典学习(ODL)和鲁棒子空间恢复(RSR)。该问题是数值上的挑战,由于其非光滑的目标和非凸约束,其算法方面还没有得到很好的探索。在本文中,我们将展示如何利用球的流形结构来设计快速算法来解决这个问题。具体而言,我们的贡献是三方面的。首先,我们提出了一个流形邻近点法(ManPPA)的问题,并表明它以次线性速度收敛。此外,我们表明,ManPPA可以实现平方收敛速率时,适用于ODL和RSR问题。其次,我们提出了一种称为StManPPA,这是非常适合于大规模计算的ManPPA的随机变体,并建立其次线性收敛速度。ManPPA和StManPPA都具有比现有的子梯度型方法更快的收敛速度。第三,使用ManPPA作为构建块,我们提出了一种新的方法来解决矩阵模拟的问题,其中球被替换为Stiefel流形。通过对ODL和RSR问题的大量数值实验,验证了所提方法的有效性。

英文摘要:

We consider the problem of maximizing the $\ell_1$ norm of a linear map over the sphere, which arises in various machine learning applications such as orthogonal dictionary learning (ODL) and robust subspace recovery (RSR). The problem is numerically challenging due to its nonsmooth objective and nonconvex constraint, and its algorithmic aspects have not been well explored. In this paper, we show how the manifold structure of the sphere can be exploited to design fast algorithms for tackling this problem. Specifically, our contribution is threefold. First, we present a manifold proximal point algorithm (ManPPA) for the problem and show that it converges at a sublinear rate. Furthermore, we show that ManPPA can achieve a quadratic convergence rate when applied to the ODL and RSR problems. Second, we propose a stochastic variant of ManPPA called StManPPA, which is well suited for large-scale computation, and establish its sublinear convergence rate. Both ManPPA and StManPPA have provably faster convergence rates than existing subgradient-type methods. Third, using ManPPA as a building block, we propose a new approach to solving a matrix analog of the problem, in which the sphere is replaced by the Stiefel manifold. The results from our extensive numerical experiments on the ODL and RSR problems demonstrate the efficiency and efficacy of our proposed methods.

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。

↑