arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.03949stat.MLcs.LGmath.PR
收藏

随机图的熵最优迁移

Entropic Optimal Transport in Random Graphs

CNRS(法国国家科学研究中心);GIPSA-lab(GIPSA实验室)

Nicolas Keriven

摘要:

在图分析中,一个经典的任务是计算节点(组)之间的相似性度量。在潜空间随机图中,节点与未知的潜变量相关联。然后,可以仅使用图结构来直接在潜在空间中计算距离。在本文中,我们表明,它是可能的一致估计熵正则化的最优运输(OT)的潜在空间中的节点组之间的距离。我们提供了一个一般的稳定性结果熵OT相对于扰动的成本矩阵。然后,我们将其应用到随机图的几个例子,如图子或$ε$-图流形。一路上,我们证明了新的浓度结果,所谓的通用奇异值holding估计,并估计测地距离流形上。

英文摘要:

In graph analysis, a classic task consists in computing similarity measures between (groups of) nodes. In latent space random graphs, nodes are associated to unknown latent variables. One may then seek to compute distances directly in the latent space, using only the graph structure. In this paper, we show that it is possible to consistently estimate entropic-regularized Optimal Transport (OT) distances between groups of nodes in the latent space. We provide a general stability result for entropic OT with respect to perturbations of the cost matrix. We then apply it to several examples of random graphs, such as graphons or $ε$-graphs on manifolds. Along the way, we prove new concentration results for the so-called Universal Singular Value Thresholding estimator, and for the estimation of geodesic distances on a manifold.

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。

↑