Beyond Log-Supermodularity: Lower Bounds and the Bethe Partition Function

Abstract

A recent result has demonstrated that the Bethe partition function always lower bounds the true partition function of binary, log-supermodular graphical models. We demonstrate that these results can be extended to other interesting classes of graphical models that are not necessarily binary or log-supermodular: the ferromagnetic Potts model with a uniform external field and its generalizations and special classes of weighted graph homomorphism problems.

Cite

Text

Ruozzi. "Beyond Log-Supermodularity: Lower Bounds and the Bethe Partition Function." Conference on Uncertainty in Artificial Intelligence, 2013.

Markdown

[Ruozzi. "Beyond Log-Supermodularity: Lower Bounds and the Bethe Partition Function." Conference on Uncertainty in Artificial Intelligence, 2013.](https://mlanthology.org/uai/2013/ruozzi2013uai-beyond/)

BibTeX

@inproceedings{ruozzi2013uai-beyond,
  title     = {{Beyond Log-Supermodularity: Lower Bounds and the Bethe Partition Function}},
  author    = {Ruozzi, Nicholas},
  booktitle = {Conference on Uncertainty in Artificial Intelligence},
  year      = {2013},
  url       = {https://mlanthology.org/uai/2013/ruozzi2013uai-beyond/}
}