DeepAI AI Chat
Log In Sign Up

On model misspecification and KL separation for Gaussian graphical models

by   Varun Jog, et al.
University of Pennsylvania
berkeley college

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, since classes of graphs exist for which the edge discrepancy increases but the KL divergence remains bounded above by a constant. As a natural corollary to our KL lower bound, we also establish a sample size requirement for correct model selection via maximum likelihood estimation. Our results rigorize the notion that it is essential to estimate the edge structure of a Gaussian graphical model accurately in order to approximate the true distribution to close precision.


page 1

page 2

page 3

page 4


On the Properties of Kullback-Leibler Divergence Between Gaussians

Kullback-Leibler (KL) divergence is one of the most important divergence...

Gaussian Graphical Model exploration and selection in high dimension low sample size setting

Gaussian Graphical Models (GGM) are often used to describe the condition...

The Quality of the Covariance Selection Through Detection Problem and AUC Bounds

We consider the problem of quantifying the quality of a model selection ...

Causal KL: Evaluating Causal Discovery

The two most commonly used criteria for assessing causal model discovery...

Samplers and extractors for unbounded functions

Blasiok (SODA'18) recently introduced the notion of a subgaussian sample...

A deterministic and computable Bernstein-von Mises theorem

Bernstein-von Mises results (BvM) establish that the Laplace approximati...