DeepAI AI Chat
Log In Sign Up

A Thorough View of Exact Inference in Graphs from the Degree-4 Sum-of-Squares Hierarchy

by   Kevin Bello, et al.

Performing inference in graphs is a common task within several machine learning problems, e.g., image segmentation, community detection, among others. For a given undirected connected graph, we tackle the statistical problem of exactly recovering an unknown ground-truth binary labeling of the nodes from a single corrupted observation of each edge. Such problem can be formulated as a quadratic combinatorial optimization problem over the boolean hypercube, where it has been shown before that one can (with high probability and in polynomial time) exactly recover the ground-truth labeling of graphs that have an isoperimetric number that grows with respect to the number of nodes (e.g., complete graphs, regular expanders). In this work, we apply a powerful hierarchy of relaxations, known as the sum-of-squares (SoS) hierarchy, to the combinatorial problem. Motivated by empirical evidence on the improvement in exact recoverability, we center our attention on the degree-4 SoS relaxation and set out to understand the origin of such improvement from a graph theoretical perspective. We show that the solution of the dual of the relaxed problem is related to finding edge weights of the Johnson and Kneser graphs, where the weights fulfill the SoS constraints and intuitively allow the input graph to increase its algebraic connectivity. Finally, as byproduct of our analysis, we derive a novel Cheeger-type lower bound for the algebraic connectivity of graphs with signed edge weights.


page 1

page 2

page 3

page 4


Fairness constraints can help exact inference in structured prediction

Many inference problems in structured prediction can be modeled as maxim...

Inferring Graphs from Cascades: A Sparse Recovery Framework

In the Network Inference problem, one seeks to recover the edges of an u...

It is better to be semi-regular when you have a low degree

We study the algebraic connectivity for several classes of random semi-r...

Finding Dominating Induced Matchings in S_1,1,5-Free Graphs in Polynomial Time

Let G=(V,E) be a finite undirected graph. An edge set E' ⊆ E is a domin...

Combinatorial Optimization via the Sum of Squares Hierarchy

We study the Sum of Squares (SoS) Hierarchy with a view towards combinat...

Optimal Grid Drawings of Complete Multipartite Graphs and an Integer Variant of the Algebraic Connectivity

How to draw the vertices of a complete multipartite graph G on different...