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 2209.03997cs.LGstat.ML
收藏

在线低秩矩阵完成

Online Low Rank Matrix Completion

Google Research(谷歌研究院)

Prateek Jain, Soumyabrata Pal

摘要:

研究了具有$\mathsf{M}$用户、$\mathsf{N}$项目和$\mathsf{T}$轮的{ \em online}低秩矩阵补全问题.在每一轮中,该算法为每个用户推荐一个项目,并从低秩用户-项目偏好矩阵中获取(噪声)奖励。我们的目标是设计一个方法与次线性遗憾(在$\mathsf{T}$)和接近最佳的依赖于$\mathsf{M}$和$\mathsf{N}$。这个问题可以很容易地映射到标准的多臂强盗问题,其中每个项目是一个{ \em独立}的手臂,但这会导致遗憾,因为手臂和用户之间的相关性没有被利用。另一方面,由于低秩流形的非凸性,利用奖励矩阵的低秩结构是具有挑战性的。我们首先证明,低秩结构可以利用一个简单的探索,然后提交(ETC)的方法,确保遗憾的$O(\mathsf{polylog} (\mathsf{M}+\mathsf{N}) \mathsf{T}^{2/3})$。也就是说,每个用户大约只需要$\mathsf{polylog} (\mathsf{M}+\mathsf{N})$项目推荐就可以获得重要的解决方案。然后,我们改进我们的排名- $1$设置,这本身是相当具有挑战性的,并封装了一些关键问题的结果。在这里,我们提出了\textsc{OCTAL}(使用迭代用户cLustering的在线协作过滤),保证了$O(\mathsf{polylog} (\mathsf{M}+\mathsf{N}) \mathsf{T}^{1/2})$几乎最佳的遗憾。OCTAL基于一种新的用户聚类技术,该技术允许迭代消除项目,并导致接近最佳的极大极小化率。

英文摘要:

We study the problem of {\em online} low-rank matrix completion with $\mathsf{M}$ users, $\mathsf{N}$ items and $\mathsf{T}$ rounds. In each round, the algorithm recommends one item per user, for which it gets a (noisy) reward sampled from a low-rank user-item preference matrix. The goal is to design a method with sub-linear regret (in $\mathsf{T}$) and nearly optimal dependence on $\mathsf{M}$ and $\mathsf{N}$. The problem can be easily mapped to the standard multi-armed bandit problem where each item is an {\em independent} arm, but that leads to poor regret as the correlation between arms and users is not exploited. On the other hand, exploiting the low-rank structure of reward matrix is challenging due to non-convexity of the low-rank manifold. We first demonstrate that the low-rank structure can be exploited using a simple explore-then-commit (ETC) approach that ensures a regret of $O(\mathsf{polylog} (\mathsf{M}+\mathsf{N}) \mathsf{T}^{2/3})$. That is, roughly only $\mathsf{polylog} (\mathsf{M}+\mathsf{N})$ item recommendations are required per user to get a non-trivial solution. We then improve our result for the rank-$1$ setting which in itself is quite challenging and encapsulates some of the key issues. Here, we propose \textsc{OCTAL} (Online Collaborative filTering using iterAtive user cLustering) that guarantees nearly optimal regret of $O(\mathsf{polylog} (\mathsf{M}+\mathsf{N}) \mathsf{T}^{1/2})$. OCTAL is based on a novel technique of clustering users that allows iterative elimination of items and leads to a nearly optimal minimax rate.

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。

↑