Ising模型结构中的广义直接变化估计
Generalized Direct Change Estimation in Ising Model Structure
摘要:
我们考虑的问题,估计两个$p$ -维伊辛模型之间的依赖结构的变化,分别基于$n_1$和$n_2$从模型中提取的样本。假设变更是结构化的,例如,稀疏、块稀疏、节点扰动稀疏等,使得它可以由合适的(原子)范数来表征。我们提出并分析了一个范数正则化估计直接估计的结构变化,而不必估计的个别伊辛模型的结构。该估计器可以使用任何范数,并且可以在温和的假设下推广到其他图形模型。我们表明,只有一组样本,说$n_2$,需要满足的估计工作的样本复杂度要求,估计误差减少为$\frac{c}{\sqrt{\min(n_1,n_2)}}$,其中$c$取决于高斯宽度的单位范数球。例如,对于应用于$s$ -稀疏变化的$\ell_1$范数,可以利用比现有结果$n_1= O(s^2 \log p)$和$n_2 = O(n_1^2)$更尖锐的$\min(n_1,n_2)=O(s \log p)$来准确地估计变化。实验结果表明所提出的估计的有效性。
英文摘要:
We consider the problem of estimating change in the dependency structure between two $p$-dimensional Ising models, based on respectively $n_1$ and $n_2$ samples drawn from the models. The change is assumed to be structured, e.g., sparse, block sparse, node-perturbed sparse, etc., such that it can be characterized by a suitable (atomic) norm. We present and analyze a norm-regularized estimator for directly estimating the change in structure, without having to estimate the structures of the individual Ising models. The estimator can work with any norm, and can be generalized to other graphical models under mild assumptions. We show that only one set of samples, say $n_2$, needs to satisfy the sample complexity requirement for the estimator to work, and the estimation error decreases as $\frac{c}{\sqrt{\min(n_1,n_2)}}$, where $c$ depends on the Gaussian width of the unit norm ball. For example, for $\ell_1$ norm applied to $s$-sparse change, the change can be accurately estimated with $\min(n_1,n_2)=O(s \log p)$ which is sharper than an existing result $n_1= O(s^2 \log p)$ and $n_2 = O(n_1^2)$. Experimental results illustrating the effectiveness of the proposed estimator are presented.
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。