On model misspecification and KL separation for Gaussian graphical models.
ISIT, pp. 1174-1178, 2015.
We establish bounds on the KL divergence between two multivariate Gaussian distributions in terms of the Hamming distance between the edge sets of the corresponding graphical models. We show that the KL divergence is bounded below by a constant when the graphs differ by at least one edge; this is essentially the tightest possible bound,...更多
下载 PDF 全文