On the Difficulty of Selecting Ising Models with Approximate Recovery

by   Jonathan Scarlett, et al.

In this paper, we consider the problem of estimating the underlying graph associated with an Ising model given a number of independent and identically distributed samples. We adopt an approximate recovery criterion that allows for a number of missed edges or incorrectly-included edges, in contrast with the widely-studied exact recovery problem. Our main results provide information-theoretic lower bounds on the sample complexity for graph classes imposing constraints on the number of edges, maximal degree, and other properties. We identify a broad range of scenarios where, either up to constant factors or logarithmic factors, our lower bounds match the best known lower bounds for the exact recovery criterion, several of which are known to be tight or near-tight. Hence, in these cases, approximate recovery has a similar difficulty to exact recovery in the minimax sense. Our bounds are obtained via a modification of Fano's inequality for handling the approximate recovery criterion, along with suitably-designed ensembles of graphs that can broadly be classed into two categories: (i) Those containing graphs that contain several isolated edges or cliques and are thus difficult to distinguish from the empty graph; (ii) Those containing graphs for which certain groups of nodes are highly correlated, thus making it difficult to determine precisely which edges connect them. We support our theoretical results on these ensembles with numerical experiments.


page 1

page 2

page 3

page 4


Lower Bounds on Active Learning for Graphical Model Selection

We consider the problem of estimating the underlying graph associated wi...

Lower Bounds for Approximating Graph Parameters via Communication Complexity

We present a new framework for proving query complexity lower bounds for...

Lower Bounds and properties for the average number of colors in the non-equivalent colorings of a graph

We study the average number 𝒜(G) of colors in the non-equivalent colorin...

Support Recovery for Orthogonal Matching Pursuit: Upper and Lower bounds

This paper studies the problem of sparse regression where the goal is to...

Information Recovery from Pairwise Measurements

This paper is concerned with jointly recovering n node-variables { x_i}_...

Community Detection and Matrix Completion with Two-Sided Graph Side-Information

We consider the problem of recovering communities of users and communiti...

Controllability Backbone in Networks

This paper studies the controllability backbone problem in dynamical net...

Please sign up or login with your details

Forgot password? Click here to reset