arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.03183stat.MLcs.LGcs.SImath.STstat.TH
收藏

图子估计的谱方法的收敛速度

Rates of Convergence of Spectral Methods for Graphon Estimation

Krannert School of Management, Purdue University(普渡大学克兰纳特管理学院)

Jiaming Xu

摘要:

本文研究了网络的生成机制--grahpon模型的估计问题。图子估计在许多应用中出现,例如预测网络中的缺失链接和在推荐系统中学习用户偏好。图子模型处理$n$顶点的随机图,使得每对两个顶点$i$和$j$以概率$ρ\times f(x_i,x_j)$独立地连接,其中$x_i$是顶点$i$的未知$d$维标签,$f$是未知对称函数,并且$ρ$是表征图稀疏性的缩放参数。最近的研究已经确定了极小极大错误率估计的graphon从一个单一的实现的随机图。然而,存在着一个很大的差距之间的已知的错误率的计算有效的估计程序和极小极大最优错误率。在这里,我们分析了谱方法,即通用奇异值阈值(USVT)算法,在相对稀疏的制度与平均顶点度$nρ=Ω(\log n)$。当$f$属于Hölder或Sobolev空间且光滑度为$α$时,我们证明了USVT的错误率至多为$(nρ)^{ -2 α/ (2α+d)}$,随着$α$的增加,USVT的错误率接近于$d=1$的极小极大最优错误率$\log (nρ)/(nρ)$.当$f$是解析的时,我们证明了USVT的错误率至多为$\log^d (nρ)/(nρ)$。在$k$块的随机块模型的特殊情况下,USVT的错误率至多为$k/(nρ)$,它比极小极大最优错误率至多大一个乘法因子$k/\log k$。这与观察到的社区检测的计算差距相吻合。我们分析的一个关键步骤是使用图子函数$f$的分段多项式近似来导出边缘概率矩阵的特征值衰减率。

英文摘要:

This paper studies the problem of estimating the grahpon model - the underlying generating mechanism of a network. Graphon estimation arises in many applications such as predicting missing links in networks and learning user preferences in recommender systems. The graphon model deals with a random graph of $n$ vertices such that each pair of two vertices $i$ and $j$ are connected independently with probability $ρ\times f(x_i,x_j)$, where $x_i$ is the unknown $d$-dimensional label of vertex $i$, $f$ is an unknown symmetric function, and $ρ$ is a scaling parameter characterizing the graph sparsity. Recent studies have identified the minimax error rate of estimating the graphon from a single realization of the random graph. However, there exists a wide gap between the known error rates of computationally efficient estimation procedures and the minimax optimal error rate. Here we analyze a spectral method, namely universal singular value thresholding (USVT) algorithm, in the relatively sparse regime with the average vertex degree $nρ=Ω(\log n)$. When $f$ belongs to Hölder or Sobolev space with smoothness index $α$, we show the error rate of USVT is at most $(nρ)^{ -2 α/ (2α+d)}$, approaching the minimax optimal error rate $\log (nρ)/(nρ)$ for $d=1$ as $α$ increases. Furthermore, when $f$ is analytic, we show the error rate of USVT is at most $\log^d (nρ)/(nρ)$. In the special case of stochastic block model with $k$ blocks, the error rate of USVT is at most $k/(nρ)$, which is larger than the minimax optimal error rate by at most a multiplicative factor $k/\log k$. This coincides with the computational gap observed for community detection. A key step of our analysis is to derive the eigenvalue decaying rate of the edge probability matrix using piecewise polynomial approximations of the graphon function $f$.

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。

↑