arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.07698stat.MLcs.ITcs.LGmath.ITmath.OCmath.STstat.TH
收藏

噪声矩阵完备化:通过非凸优化理解凸松弛的统计保证

Noisy Matrix Completion: Understanding Statistical Guarantees for Convex Relaxation via Nonconvex Optimization

Princeton University(普林斯顿大学);Carnegie Mellon University(卡内基梅隆大学)

Yuxin Chen, Yuejie Chi, Jianqing Fan, Cong Ma, Yuling Yan

摘要:

本文研究了噪声低秩矩阵的完备化问题:给定一个大型低秩矩阵的部分和噪声元素,目标是忠实而有效地估计底层矩阵。可以说,解决这个问题的最流行的范例之一是凸松弛,它在实践中取得了显着的效果。然而,这种方法的理论支持在噪声环境中仍然远远不是最佳的,无法解释其经验上的成功。我们取得了进展,对神秘的凸松弛与随机噪声的实际效果。当未知矩阵的秩和条件数是由一个常数的范围内,我们证明了凸规划方法实现了近最佳的估计误差--在欧氏损失,entrywise损失,和频谱范数损失-在很宽的范围内的噪声水平。所有这些都是通过将凸松弛与非凸Burer-Monteiro方法连接起来实现的,这是一种看似独特的算法范例,可证明对噪声具有鲁棒性。更具体地说,我们表明,一个近似的临界点的非凸制定作为一个非常紧密的近似凸的解决方案,从而使我们能够转移所需的统计保证的非凸的方法,其凸对应。

英文摘要:

This paper studies noisy low-rank matrix completion: given partial and noisy entries of a large low-rank matrix, the goal is to estimate the underlying matrix faithfully and efficiently. Arguably one of the most popular paradigms to tackle this problem is convex relaxation, which achieves remarkable efficacy in practice. However, the theoretical support of this approach is still far from optimal in the noisy setting, falling short of explaining its empirical success. We make progress towards demystifying the practical efficacy of convex relaxation vis-à-vis random noise. When the rank and the condition number of the unknown matrix are bounded by a constant, we demonstrate that the convex programming approach achieves near-optimal estimation errors --- in terms of the Euclidean loss, the entrywise loss, and the spectral norm loss --- for a wide range of noise levels. All of this is enabled by bridging convex relaxation with the nonconvex Burer-Monteiro approach, a seemingly distinct algorithmic paradigm that is provably robust against noise. More specifically, we show that an approximate critical point of the nonconvex formulation serves as an extremely tight approximation of the convex solution, thus allowing us to transfer the desired statistical guarantees of the nonconvex approach to its convex counterpart.

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。

↑