PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Approximation Bounds for Inference using Cooperative Cut
Stefanie Jegelka and Jeff Bilmes
In: ICML 2011, 28 June - 02 July, Bellevue, USA.

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.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:8781
Deposited By:Stefanie Jegelka
Deposited On:21 February 2012