Inferring with high girth graphical models

Uri Heinemann, Amir Globerson

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Unsupervised learning of graphical models is an important task in many domains. Although maximum likelihood learning is computationally hard, there do exist consistent learning algorithms (e.g., psuedo-likelihood and its variants). However, inference in the learned models is still hard, and thus they are not directly usable. In other words, given a probabilistic query they are not guaranteed to provide an answer that is close to the true one. In the current paper, we provide a learning al-gorithm that is guaranteed to provide approximately correct probabilistic inference. We focus on a particular class of models, namely high girth graphs in the correlation decay regime. It is well known that approximate inference (e.g, using loopy BP) in such models yields marginals that are close to the true ones. Motivated by this, we propose an algorithm that always returns models of this type, and hence in the models it returns inference is approximately correct. We derive finite sample results guaranteeing that beyond a certain sample size, the resulting models will answer probabilistic queries with a high level of accuracy. Results on synthetic data show that the models we learn indeed outperform those obtained by other algorithms, which do not return high girth graphs.

Original languageEnglish
Title of host publication31st International Conference on Machine Learning, ICML 2014
PublisherInternational Machine Learning Society (IMLS)
Number of pages20
ISBN (Electronic)9781634393973
StatePublished - 2014
Externally publishedYes
Event31st International Conference on Machine Learning, ICML 2014 - Beijing, China
Duration: 21 Jun 201426 Jun 2014

Publication series

Name31st International Conference on Machine Learning, ICML 2014


Conference31st International Conference on Machine Learning, ICML 2014


Dive into the research topics of 'Inferring with high girth graphical models'. Together they form a unique fingerprint.

Cite this