DeepAI AI Chat
Log In Sign Up

Interpreting Graph Cuts as a Max-Product Algorithm

by   Daniel Tarlow, et al.

The maximum a posteriori (MAP) configuration of binary variable models with submodular graph-structured energy functions can be found efficiently and exactly by graph cuts. Max-product belief propagation (MP) has been shown to be suboptimal on this class of energy functions by a canonical counterexample where MP converges to a suboptimal fixed point (Kulesza & Pereira, 2008). In this work, we show that under a particular scheduling and damping scheme, MP is equivalent to graph cuts, and thus optimal. We explain the apparent contradiction by showing that with proper scheduling and damping, MP always converges to an optimal fixed point. Thus, the canonical counterexample only shows the suboptimality of MP with a particular suboptimal choice of schedule and damping. With proper choices, MP is optimal.


page 1

page 2

page 3

page 4


On the optimality of tree-reweighted max-product message-passing

Tree-reweighted max-product (TRW) message passing is a modified form of ...

Zero-Temperature Limit of a Convergent Algorithm to Minimize the Bethe Free Energy

After the discovery that fixed points of loopy belief propagation coinci...

Loopy Belief Propagation, Bethe Free Energy and Graph Zeta Function

We propose a new approach to the theoretical analysis of Loopy Belief Pr...

Graph Zeta Function in the Bethe Free Energy and Loopy Belief Propagation

We propose a new approach to the analysis of Loopy Belief Propagation (L...

Reasoning about Social Choice and Games in Monadic Fixed-Point Logic

Whether it be in normal form games, or in fair allocations, or in voter ...

Binary Diffing as a Network Alignment Problem via Belief Propagation

In this paper, we address the problem of finding a correspondence, or ma...

Derandomized Load Balancing using Random Walks on Expander Graphs

In a computing center with a huge amount of machines, when a job arrives...