Conference item icon

Conference item

Linear and Parallel Learning for Markov Random Fields

Abstract:
We introduce a new embarrassingly parallel parameter learning algorithm for Markov random fields 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.

Actions


Access Document


Files:

Authors


Yariv Dror Mizrahi More by this author
Misha Denil More by this author
Nando de Freitas More by this author
Publication date:
2014
URN:
uuid:97f20223-6c50-4faf-b150-85b7c10facf4
Local pid:
cs:8647

Terms of use


Metrics



If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP