arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.06237cs.LGcs.CCcs.DScs.ITmath.ITstat.ML
收藏

张量平方和完备化

Exact tensor completion with sum-of-squares

Institute for Advanced Study(高等研究院);Cornell University(康奈尔大学)

Aaron Potechin, David Steurer

摘要:

我们获得了第一个多项式时间算法的精确张量完成,提高了减少矩阵完成所隐含的界限。该算法从$r\cdot \tilde O(n^{1.5})$随机观察到的张量条目中恢复出一个未知的3-张量,其中$r$是$\mathbb R^n$中的非相干正交分量。这个界限改善了以前的最好的一个$r\cdot \tilde O(n^{2})$减少到确切的矩阵完成。我们的界也与最著名的结果相匹配,因为近似张量完成的问题更容易(Barak & Moitra,2015)。我们的算法和分析通过平方和方法将精确矩阵完成(Candes & Recht,2009)的开创性结果扩展到张量设置。主要的技术挑战是要证明少量随机选择的单项式就足以在球面上构造一个具有精确种植的正交全局最优解的3次多项式,并且这个事实可以在平方和证明系统中得到证明。

英文摘要:

We obtain the first polynomial-time algorithm for exact tensor completion that improves over the bound implied by reduction to matrix completion. The algorithm recovers an unknown 3-tensor with $r$ incoherent, orthogonal components in $\mathbb R^n$ from $r\cdot \tilde O(n^{1.5})$ randomly observed entries of the tensor. This bound improves over the previous best one of $r\cdot \tilde O(n^{2})$ by reduction to exact matrix completion. Our bound also matches the best known results for the easier problem of approximate tensor completion (Barak & Moitra, 2015). Our algorithm and analysis extends seminal results for exact matrix completion (Candes & Recht, 2009) to the tensor setting via the sum-of-squares method. The main technical challenge is to show that a small number of randomly chosen monomials are enough to construct a degree-3 polynomial with precisely planted orthogonal global optima over the sphere and that this fact can be certified within the sum-of-squares proof system.

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。

↑