Time varying undirected graphs
Time varying undirected graphs
复制标题
DOI：
10.1007/s10994-010-5180-0
复制
发表时间：
2010-09-01
期刊：
影响因子：
7.5
通讯作者：
Wasserman, Larry
中科院分区：
文献类型：
--
作者：
Zhou, Shuheng;Lafferty, John;Wasserman, Larry
无向图通常用来描述高维分布。在稀疏条件下，可以使用“”(1)惩罚方法来估计图。然而，目前的方法假定数据是独立的和相同分布的。如果分布以及图表随着时间的推移而演变，那么数据就不再是同分布的。本文利用a“”(1)正则化方法，提出了一种估计多元高斯分布时变图结构的非参数方法，并证明了，只要协方差随时间平滑变化，即使p很大，我们也能很好地估计协方差矩阵(在预测风险中)。
Undirected graphs are often used to describe high dimensional distributions. Under sparsity conditions, the graph can be estimated using a"" (1) penalization methods. However, current methods assume that the data are independent and identically distributed. If the distribution, and hence the graph, evolves over time then the data are not longer identically distributed. In this paper we develop a nonparametric method for estimating time varying graphical structure for multivariate Gaussian distributions using an a"" (1) regularization method, and show that, as long as the covariances change smoothly over time, we can estimate the covariance matrix well (in predictive risk) even when p is large.