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 1801.00368math.NAcs.NA
收藏

秩一矩阵补全问题通过两次半正定松弛得以解决

Stable rank one matrix completion is solved by two rounds of semidefinite programming relaxation

Département de Mathématiques et Applications, Ecole Normale Supérieure, Ulm, Paris. PSL Research University(巴黎高等师范学院数学与应用系);Department of Mathematics, Massachusetts Institute of Technology(麻省理工学院数学系)

Augustin Cosse, Laurent Demanet

AI总结:

本文研究确定性秩一矩阵补全问题,证明通过两次半正定松弛可恢复原始矩阵,且解对观测条目扰动具有Lipschitz稳定性。

摘要:

本文研究确定性秩一矩阵补全问题。已知最简单的半正定松弛(最小化核范数)通常无法解决此问题。本文证明在问题有唯一解的情况下,通过两次半正定松弛(最小化迹范数)可确定性恢复原始矩阵。进一步证明所提半正定程序的解对观测条目扰动具有Lipschitz稳定性,不同于非线性传播或岭回归等基本算法。证明基于递归构建对应对偶sum-of-squares(SOS)多项式的证书。该SOS多项式由补全约束生成的多项式理想和最小化迹提供的单项式构建。所提松弛方法属于Lasserre层次框架,但关键增加了迹目标函数。进一步展示如何通过分层低秩分解以有利复杂度表示和操作矩量张量。

英文摘要:

This paper studies the problem of deterministic rank-one matrix completion. It is known that the simplest semidefinite programming relaxation, involving minimization of the nuclear norm, does not in general return the solution for this problem. In this paper, we show that in every instance where the problem has a unique solution, one can provably recover the original matrix through two rounds of semidefinite programming relaxation with minimization of the trace norm. We further show that the solution of the proposed semidefinite program is Lipschitz-stable with respect to perturbations of the observed entries, unlike more basic algorithms such as nonlinear propagation or ridge regression. Our proof is based on recursively building a certificate of optimality corresponding to a dual sum-of-squares (SOS) polynomial. This SOS polynomial is built from the polynomial ideal generated by the completion constraints and the monomials provided by the minimization of the trace. The proposed relaxation fits in the framework of the Lasserre hierarchy, albeit with the key addition of the trace objective function. We further show how to represent and manipulate the moment tensor in favorable complexity by means of a hierarchical low-rank decomposition.

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。

↑