arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0910.5260math.NAcs.LGcs.NA
收藏

格拉斯曼流形上的梯度下降算法用于矩阵补全

A Gradient Descent Algorithm on the Grassman Manifold for Matrix Completion

Raghunandan H. Keshavan, Sewoong Oh

AI总结:

提出基于奇异值分解和局部流形优化的OptSpace算法,从少量观测条目中精确恢复低秩矩阵。

摘要:

我们考虑从少量观测条目中重构低秩矩阵的问题。本文描述了一种高效算法OptSpace的实现,该算法基于奇异值分解后接局部流形优化,用于解决低秩矩阵补全问题。已有研究表明,如果观测条目数量足够大,奇异值分解的输出能给出原始矩阵的良好估计,从而局部优化能以高概率重构出正确矩阵。我们给出的数值结果表明,该算法能从极少量观测条目中精确重构低秩矩阵。我们进一步研究了算法对噪声的鲁棒性,以及在实际协同过滤数据集上的性能。

英文摘要:

We consider the problem of reconstructing a low-rank matrix from a small subset of its entries. In this paper, we describe the implementation of an efficient algorithm called OptSpace, based on singular value decomposition followed by local manifold optimization, for solving the low-rank matrix completion problem. It has been shown that if the number of revealed entries is large enough, the output of singular value decomposition gives a good estimate for the original matrix, so that local optimization reconstructs the correct matrix with high probability. We present numerical results which show that this algorithm can reconstruct the low rank matrix exactly from a very small subset of its entries. We further study the robustness of the algorithm with respect to noise, and its performance on actual collaborative filtering datasets.

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。

↑