Approximation Bounds for Inference Using Cooperative Cuts

Abstract

We analyze a family of probability distributions that are characterized by an embedded combinatorial structure. This family includes models having arbitrary treewidth and arbitrary sized factors. Unlike general models with such freedom, where the �most probable explanation� (MPE) problem is inapproximable, the combinatorial structure within our model, in particular the indirect use of submodularity, leads to several MPE algorithms that all have approximation guarantees.

Cite

Text

Jegelka and Bilmes. "Approximation Bounds for Inference Using Cooperative Cuts." International Conference on Machine Learning, 2011.

Markdown

[Jegelka and Bilmes. "Approximation Bounds for Inference Using Cooperative Cuts." International Conference on Machine Learning, 2011.](https://mlanthology.org/icml/2011/jegelka2011icml-approximation/)

BibTeX

@inproceedings{jegelka2011icml-approximation,
  title     = {{Approximation Bounds for Inference Using Cooperative Cuts}},
  author    = {Jegelka, Stefanie and Bilmes, Jeff A.},
  booktitle = {International Conference on Machine Learning},
  year      = {2011},
  pages     = {577-584},
  url       = {https://mlanthology.org/icml/2011/jegelka2011icml-approximation/}
}