arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1304.4672stat.ML
收藏

基于自适应采样的低秩矩阵和张量完备化

Low-Rank Matrix and Tensor Completion via Adaptive Sampling

Akshay Krishnamurthy, Aarti Singh

摘要:

我们研究了低秩矩阵和张量完成,并提出了新的算法,采用自适应采样方案,以获得强大的性能保证。我们的算法利用自适应性来识别对于学习矩阵(张量)的列空间具有高度信息性的条目,因此,即使当行空间高度一致时,我们的结果也成立,与以前的分析相反。在没有噪声的情况下,我们表明,可以准确地恢复$n \times n$矩阵的秩$r$从仅仅$Ω(n r^{3/2}\log(r))$矩阵条目。我们还表明,可以恢复一个订单$T$张量使用$Ω(n r^{T-1/2}T^2 \log(r))$条目。对于有噪声的恢复,我们的算法始终估计一个低秩矩阵损坏的噪声使用$Ω(n r^{3/2} \textrm{polylog}(n))$条目。我们补充我们的研究与模拟,验证我们的理论,并证明我们的算法的可扩展性。

英文摘要:

We study low rank matrix and tensor completion and propose novel algorithms that employ adaptive sampling schemes to obtain strong performance guarantees. Our algorithms exploit adaptivity to identify entries that are highly informative for learning the column space of the matrix (tensor) and consequently, our results hold even when the row space is highly coherent, in contrast with previous analyses. In the absence of noise, we show that one can exactly recover a $n \times n$ matrix of rank $r$ from merely $Ω(n r^{3/2}\log(r))$ matrix entries. We also show that one can recover an order $T$ tensor using $Ω(n r^{T-1/2}T^2 \log(r))$ entries. For noisy recovery, our algorithm consistently estimates a low rank matrix corrupted with noise using $Ω(n r^{3/2} \textrm{polylog}(n))$ entries. We complement our study with simulations that verify our theory and demonstrate the scalability of our algorithms.

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。

↑