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 1306.0626cs.LGcs.ITmath.ITstat.ML
收藏

可证归纳矩阵完备化

Provable Inductive Matrix Completion

Microsoft Research India(微软印度研究院);The University of Texas at Austin(德克萨斯大学奥斯汀分校)

Prateek Jain, Inderjit S. Dhillon

摘要:

考虑一个电影推荐系统,其中除了评级信息之外,诸如用户年龄或电影类型的辅助信息也是可用的。与标准的矩阵补全不同,在这种设置中,应该能够对新用户/电影进行归纳预测。本文研究了在精确恢复情形下的归纳矩阵完备化问题。也就是说,我们假设评级矩阵是通过将特征向量应用于低秩矩阵而生成的,目标是恢复底层矩阵。此外,我们推广的问题,低秩矩阵估计秩1测量。我们研究这个一般性的问题,并提供条件的测量集应满足,使交替最小化方法(否则是一个非凸的方法,没有收敛保证)是能够恢复回{ \em确切}底层低秩矩阵。除了归纳矩阵完成,我们表明,其他两个低秩估计问题可以在我们的框架中进行研究:a)一般低秩矩阵检测秩1测量,和b)多标签回归缺失标签。对于这两个问题,我们提供了新的和有趣的界限交替最小化所需的测量的数量可证明收敛到{ \em精确}低秩矩阵。特别是,我们对一般低秩矩阵传感问题的分析显着提高了所需的存储和计算成本比所需的RIP为基础的矩阵传感方法\cite{RechtFP2007}。最后,我们提供了我们的方法的实证验证,并证明交替最小化是能够使用少量的测量恢复上述问题的真实矩阵。

英文摘要:

Consider a movie recommendation system where apart from the ratings information, side information such as user's age or movie's genre is also available. Unlike standard matrix completion, in this setting one should be able to predict inductively on new users/movies. In this paper, we study the problem of inductive matrix completion in the exact recovery setting. That is, we assume that the ratings matrix is generated by applying feature vectors to a low-rank matrix and the goal is to recover back the underlying matrix. Furthermore, we generalize the problem to that of low-rank matrix estimation using rank-1 measurements. We study this generic problem and provide conditions that the set of measurements should satisfy so that the alternating minimization method (which otherwise is a non-convex method with no convergence guarantees) is able to recover back the {\em exact} underlying low-rank matrix. In addition to inductive matrix completion, we show that two other low-rank estimation problems can be studied in our framework: a) general low-rank matrix sensing using rank-1 measurements, and b) multi-label regression with missing labels. For both the problems, we provide novel and interesting bounds on the number of measurements required by alternating minimization to provably converges to the {\em exact} low-rank matrix. In particular, our analysis for the general low rank matrix sensing problem significantly improves the required storage and computational cost than that required by the RIP-based matrix sensing methods \cite{RechtFP2007}. Finally, we provide empirical validation of our approach and demonstrate that alternating minimization is able to recover the true matrix for the above mentioned problems using a small number of measurements.

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。

↑