TY - GEN

T1 - Approximation bounds for inference using cooperative cuts

AU - Jegelka, Stefanie

AU - Bilmes, Jeff

PY - 2011

Y1 - 2011

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=80053454291&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:80053454291

SN - 9781450306195

T3 - Proceedings of the 28th International Conference on Machine Learning, ICML 2011

SP - 577

EP - 584

BT - Proceedings of the 28th International Conference on Machine Learning, ICML 2011

T2 - 28th International Conference on Machine Learning, ICML 2011

Y2 - 28 June 2011 through 2 July 2011

ER -