A Novel Approach for Markov Random Field With Intractable Normalizing Constant on Large Lattices

What is it about?

We have proposed a new method to tackle the normalizing constant problem in Potts model. We capitalized the conditional independence structure in the Potts models, and decomposed the large Potts model field into some small one. Therefore the normalizing constant of the original Potts model is translated into small Potts model fields.

Featured Image

Why is it important?

It improves the estimation efficiency of the Potts models as shown in the paper.