Consider a random, symmetric perturbation of a symmetric, low rank matrix. The goal of this paper is to present entry-wise bounds on the perturbation of the singular vectors. In particular, our result shows that, under common incoherence assumptions, the entry-wise error is evenly dissipated. This improves a number of previous results and has algorithmic applications for many well known clustering problems, including the hidden clique, planted coloring, and planted bipartition.
翻译:考虑对称、低秩矩阵的随机对称扰动。本文的目标是呈现奇异向量的入口限制扰动。特别地,我们的结果表明,在常见的不相干假设下,入口误差是均匀耗散的。这改进了许多先前的结果,并对许多众所周知的聚类问题,包括隐藏的团,种植物着色和种植双分区具有算法应用。