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 2402.15095math.STcs.DScs.LGmath.PRstat.TH
收藏

在低维情形下匹配相关高斯几何模型的Umeyama算法

The Umeyama algorithm for matching correlated Gaussian geometric models in the low-dimensional regime

Peking University(北京大学)

Shuyang Gong, Zhangsong Li

AI总结:

本文研究了在低维情形下通过潜在节点排列关联的两个高斯几何模型的匹配问题,证明了Umeyama算法在特定噪声条件下可实现精确或近似恢复排列。

摘要:

受匹配两个相关随机几何图问题的启发,我们研究了通过潜在节点排列关联的两个高斯几何模型的匹配问题。具体来说,给定一个未知的排列π*在{1,…,n}上,以及n个i.i.d.的关联高斯向量{X_{π*(i)},Y_i}在R^d中,带有噪声参数σ,考虑两种类型的(相关)加权完全图,边权重由A_{i,j}=⟨X_i,X_j⟩,B_{i,j}=⟨Y_i,Y_j⟩给出。目标是基于观测到的矩阵A和B恢复隐藏的顶点对应关系π*。在低维情形下(d=O(log n)),Wang, Wu, Xu, and Yolou [WWXY22+]建立了匹配相关高斯几何模型的精确和近似恢复的信息阈值,并进行了经典Umeyama算法的数值实验。在本文中,我们证明该算法在噪声参数σ=o(d^{-3}n^{-2/d})时实现π*的精确恢复,在σ=o(d^{-3}n^{-1/d})时实现近似恢复。我们的结果在低维情形下接近信息阈值,仅相差一个poly(d)因子。

英文摘要:

Motivated by the problem of matching two correlated random geometric graphs, we study the problem of matching two Gaussian geometric models correlated through a latent node permutation. Specifically, given an unknown permutation $π^*$ on $\{1,\ldots,n\}$ and given $n$ i.i.d. pairs of correlated Gaussian vectors $\{X_{π^*(i)},Y_i\}$ in $\mathbb{R}^d$ with noise parameter $σ$, we consider two types of (correlated) weighted complete graphs with edge weights given by $A_{i,j}=\langle X_i,X_j \rangle$, $B_{i,j}=\langle Y_i,Y_j \rangle$. The goal is to recover the hidden vertex correspondence $π^*$ based on the observed matrices $A$ and $B$. For the low-dimensional regime where $d=O(\log n)$, Wang, Wu, Xu, and Yolou [WWXY22+] established the information thresholds for exact and almost exact recovery in matching correlated Gaussian geometric models. They also conducted numerical experiments for the classical Umeyama algorithm. In our work, we prove that this algorithm achieves exact recovery of $π^*$ when the noise parameter $σ=o(d^{-3}n^{-2/d})$, and almost exact recovery when $σ=o(d^{-3}n^{-1/d})$. Our results approach the information thresholds up to a $\operatorname{poly}(d)$ factor in the low-dimensional regime.

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。

↑