English

On the Partition Function and Random Maximum A-Posteriori Perturbations

Machine Learning 2012-07-03 v1 Machine Learning

Abstract

In this paper we relate the partition function to the max-statistics of random variables. In particular, we provide a novel framework for approximating and bounding the partition function using MAP inference on randomly perturbed models. As a result, we can use efficient MAP solvers such as graph-cuts to evaluate the corresponding partition function. We show that our method excels in the typical "high signal - high coupling" regime that results in ragged energy landscapes difficult for alternative approaches.

Keywords

Cite

@article{arxiv.1206.6410,
  title  = {On the Partition Function and Random Maximum A-Posteriori Perturbations},
  author = {Tamir Hazan and Tommi Jaakkola},
  journal= {arXiv preprint arXiv:1206.6410},
  year   = {2012}
}

Comments

Appears in Proceedings of the 29th International Conference on Machine Learning (ICML 2012)

R2 v1 2026-06-21T21:26:44.686Z