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 1102.2254stat.MLcs.ITmath.IT
收藏

具有列操作的矩阵完备化:接近最优的样本-鲁棒性-秩权衡

Matrix completion with column manipulation: Near-optimal sample-robustness-rank tradeoffs

Yudong Chen, Huan Xu, Constantine Caramanis, Sujay Sanghavi

摘要:

本文考虑矩阵完备化问题时,一些列完全和任意损坏,潜在的恶意对手。众所周知,矩阵补全的标准算法可以返回任意差的结果,即使是一列损坏。一个直接的应用来自健壮的协同过滤。在这里,一些用户是所谓的操纵者,他们试图通过校准他们对系统的输入来扭曲算法的预测。在本文中,我们开发了一个有效的算法,这个问题的基础上结合的修剪程序和凸规划,最大限度地减少核范数和$\ell_{1,2}$规范。我们的理论结果表明,给定一个消失的分数观察到的条目,它仍然是可能的,以完成底层矩阵,即使损坏的列的数量增长。值得注意的是,我们的结果没有对操作列的观察条目的位置或值进行任何假设。此外,我们通过信息理论的论证表明,我们的保证在真实列上的采样条目的分数、损坏列的分数和底层矩阵的秩方面几乎是最优的。因此,我们的研究结果尖锐的特点之间的权衡样本,鲁棒性和秩矩阵完成。

英文摘要:

This paper considers the problem of matrix completion when some number of the columns are completely and arbitrarily corrupted, potentially by a malicious adversary. It is well-known that standard algorithms for matrix completion can return arbitrarily poor results, if even a single column is corrupted. One direct application comes from robust collaborative filtering. Here, some number of users are so-called manipulators who try to skew the predictions of the algorithm by calibrating their inputs to the system. In this paper, we develop an efficient algorithm for this problem based on a combination of a trimming procedure and a convex program that minimizes the nuclear norm and the $\ell_{1,2}$ norm. Our theoretical results show that given a vanishing fraction of observed entries, it is nevertheless possible to complete the underlying matrix even when the number of corrupted columns grows. Significantly, our results hold without any assumptions on the locations or values of the observed entries of the manipulated columns. Moreover, we show by an information-theoretic argument that our guarantees are nearly optimal in terms of the fraction of sampled entries on the authentic columns, the fraction of corrupted columns, and the rank of the underlying matrix. Our results therefore sharply characterize the tradeoffs between sample, robustness and rank in matrix completion.

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。

↑