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.
| Author(s): | Jegelka, S. and Bilmes, J. |
| Pages: | 577-584 |
| Year: | 2011 |
| Month: | July |
| Day: | 0 |
| Editors: | Getoor, L. , T. Scheffer |
| Publisher: | International Machine Learning Society |
| Bibtex Type: | Conference Paper (inproceedings) |
| Address: | Madison, WI, USA |
| Event Name: | 28th International Conference on Machine Learning (ICML 2011) |
| Event Place: | Bellevue, WA, USA |
| Digital: | 0 |
| Electronic Archiving: | grant_archive |
| ISBN: | 978-1-450-30619-5 |
| Links: | |
BibTex
@inproceedings{JegelkaB2011_2,
title = {Approximation Bounds for Inference using Cooperative Cut},
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. },
pages = {577-584},
editors = {Getoor, L. , T. Scheffer},
publisher = {International Machine Learning Society},
address = {Madison, WI, USA},
month = jul,
year = {2011},
slug = {jegelkab2011_2},
author = {Jegelka, S. and Bilmes, J.},
month_numeric = {7}
}