arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 0910.0413cs.ITmath.IT
收藏

从少量线性测量中精确恢复低秩矩阵

Accurate low-rank matrix recovery from a small number of linear measurements

Emmanuel J. Candes, Yaniv Plan

摘要:

我们考虑从少量随机线性测量中恢复低秩矩阵M的问题。这个问题的一个流行而有用的例子是矩阵完成,其中测量揭示了条目子集的值,我们希望填充缺失的条目(这是着名的Netflix问题)。当M被认为具有低秩时,理想情况下会试图通过找到与数据一致的最小秩矩阵来恢复M;然而,这是有问题的,因为这是一个非凸问题,通常是棘手的。核范数最小化已经被提出作为一种易于处理的方法,过去的论文已经深入研究了核范数最小化算法的理论性质,建立了最小化核范数产生最小秩解的条件。我们回顾了今年春天的新兴文献,并扩展和完善以前的理论结果。我们的重点是提供误差界时,M是很好地近似一个低秩矩阵,当测量与噪声损坏。我们发现,对于某一类随机线性测量,核范数最小化提供了稳定的恢复,从一些样本几乎在理论下限,并享有秩序最优的误差界(高概率)。

英文摘要:

We consider the problem of recovering a lowrank matrix M from a small number of random linear measurements. A popular and useful example of this problem is matrix completion, in which the measurements reveal the values of a subset of the entries, and we wish to fill in the missing entries (this is the famous Netflix problem). When M is believed to have low rank, one would ideally try to recover M by finding the minimum-rank matrix that is consistent with the data; this is, however, problematic since this is a nonconvex problem that is, generally, intractable. Nuclear-norm minimization has been proposed as a tractable approach, and past papers have delved into the theoretical properties of nuclear-norm minimization algorithms, establishing conditions under which minimizing the nuclear norm yields the minimum rank solution. We review this spring of emerging literature and extend and refine previous theoretical results. Our focus is on providing error bounds when M is well approximated by a low-rank matrix, and when the measurements are corrupted with noise. We show that for a certain class of random linear measurements, nuclear-norm minimization provides stable recovery from a number of samples nearly at the theoretical lower limit, and enjoys order-optimal error bounds (with high probability).

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。

↑