Alert button
Picture for Yariv Dror Mizrahi

Yariv Dror Mizrahi

Alert button

Distributed Parameter Estimation in Probabilistic Graphical Models

Add code
Bookmark button
Alert button
Jun 11, 2014
Yariv Dror Mizrahi, Misha Denil, Nando de Freitas

Figure 1 for Distributed Parameter Estimation in Probabilistic Graphical Models
Figure 2 for Distributed Parameter Estimation in Probabilistic Graphical Models

This paper presents foundational theoretical results on distributed parameter estimation for undirected probabilistic graphical models. It introduces a general condition on composite likelihood decompositions of these models which guarantees the global consistency of distributed estimators, provided the local estimators are consistent.

Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

Linear and Parallel Learning of Markov Random Fields

Add code
Bookmark button
Alert button
Feb 05, 2014
Yariv Dror Mizrahi, Misha Denil, Nando de Freitas

Figure 1 for Linear and Parallel Learning of Markov Random Fields
Figure 2 for Linear and Parallel Learning of Markov Random Fields
Figure 3 for Linear and Parallel Learning of Markov Random Fields
Figure 4 for Linear and Parallel Learning of Markov Random Fields

We introduce a new embarrassingly parallel parameter learning algorithm for Markov random fields with untied parameters which is efficient for a large class of practical models. Our algorithm parallelizes naturally over cliques and, for graphs of bounded degree, its complexity is linear in the number of cliques. Unlike its competitors, our algorithm is fully parallel and for log-linear models it is also data efficient, requiring only the local sufficient statistics of the data to estimate parameters.

Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon