arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.00530math.STstat.MEstat.TH
收藏

高维Ising模型中的张量恢复

Tensor Recovery in High-Dimensional Ising Models

Tianyu Liu, Somabha Mukherjee, Rahul Biswas

AI总结:

本文针对高维$k$-张量Ising模型的张量参数恢复问题,提出基于$\boldsymbol{\textit{l}}_1$正则化逐节点逻辑回归的惩罚方法,推导了高维情形下符号支撑集一致恢复的样本量条件,并通过仿真和小鼠视觉皮层电生理数据验证了方法有效性。

摘要:

$k$-张量Ising模型是定义在$p$维二元超立方体上的指数族模型,用于建模相依二元数据,其充分统计量由观测值的所有$k$阶乘积构成,参数为未知的$k$阶张量,用于捕捉二元变量之间的高阶交互作用。本文提出一种基于惩罚技术的方法,在真实张量的所有元素都不过于接近零的假设下,能够以高概率恢复张量参数的符号支撑集。该方法基于$\boldsymbol{\textit{l}}_1$正则化的逐节点逻辑回归,可高概率恢复每个节点的符号邻域。我们的分析在高维情形下开展,允许Ising模型的维度$p$以及交互阶数$k$随样本量$n$一同增长至无穷大。研究表明,若最小交互强度不太小,当样本量满足$n = Ω((k!)^8 d^3 \binom{p-1}{k-1})$时,可实现整个符号支撑集的一致恢复,其中$d$表示所研究超网络的最大度。我们在两种仿真设置下验证了结果,并将其应用于一个真实神经生物学数据集——该数据集包含来自小鼠视觉皮层的多阵列电生理记录——以建模脑区之间的高阶交互作用。

英文摘要:

The $k$-tensor Ising model is an exponential family on a $p$-dimensional binary hypercube for modeling dependent binary data, where the sufficient statistic consists of all $k$-fold products of the observations, and the parameter is an unknown $k$-fold tensor, designed to capture higher-order interactions between the binary variables. In this paper, we describe an approach based on a penalization technique that helps us recover the signed support of the tensor parameter with high probability, assuming that no entry of the true tensor is too close to zero. The method is based on an $\ell_1$-regularized node-wise logistic regression, that recovers the signed neighborhood of each node with high probability. Our analysis is carried out in the high-dimensional regime, that allows the dimension $p$ of the Ising model, as well as the interaction factor $k$ to potentially grow to $\infty$ with the sample size $n$. We show that if the minimum interaction strength is not too small, then consistent recovery of the entire signed support is possible if one takes $n = Ω((k!)^8 d^3 \log \binom{p-1}{k-1})$ samples, where $d$ denotes the maximum degree of the hypernetwork in question. Our results are validated in two simulation settings, and applied on a real neurobiological dataset consisting of multi-array electro-physiological recordings from the mouse visual cortex, to model higher-order interactions between the brain regions.

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。

↑