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.
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)