Graph cuts always find a global optimum for Potts models (with a catch)

TL;DR

This paper proves that the α-expansion algorithm for MAP inference in Potts models finds a global optimum for slightly perturbed problems, explaining its practical success in computer vision.

Contribution

It establishes that graph cuts algorithms are globally optimal for perturbed instances of Potts models and provides a certification method for solution stability.

Findings

α-expansion finds global optima for small perturbations.

Solutions to perturbed problems are close to original solutions.

The certification algorithm confirms solution stability in practice.

Abstract

We prove that the $\alpha$-expansion algorithm for MAP inference always returns a globally optimal assignment for Markov Random Fields with Potts pairwise potentials, with a catch: the returned assignment is only guaranteed to be optimal for an instance within a small perturbation of the original problem instance. In other words, all local minima with respect to expansion moves are global minima to slightly perturbed versions of the problem. On "real-world" instances, MAP assignments of small perturbations of the problem should be very similar to the MAP assignment(s) of the original problem instance. We design an algorithm that can certify whether this is the case in practice. On several MAP inference problem instances from computer vision, this algorithm certifies that MAP solutions to all of these perturbations are very close to solutions of the original instance. These results taken together give a cohesive explanation for the good performance of "graph cuts" algorithms in practice. Every local expansion minimum is a global minimum in a small perturbation of the problem, and all of these global minima are close to the original solution.