In EM and related algorithms, E-step computations distribute easily, because data items are independent given parameters. For very large data sets, however, even storing all of the parameters in a single node for the M-step can be prohibitive. We present a framework which exploits parameter sparsity to fully distribute the entire EM procedure. Each node interacts with only the subset of parameters relevant to its data, sending messages to other nodes along a junction-tree topology. We demonstrate the effectiveness of our framework over a MapReduce approach, on two tasks: word alignment for machine translation, and LDA for topic modeling.
Title
Fully Distributed EM for Very Large Datasets
Published
2007-12-22
Full Collection Name
Electrical Engineering & Computer Sciences Technical Reports
Other Identifiers
EECS-2007-178
Type
Text
Extent
10 p
Archive
The Engineering Library
Usage Statement
Researchers may make free and open use of the UC Berkeley Library’s digitized public domain materials. However, some materials in our online collections may be protected by U.S. copyright law (Title 17, U.S.C.). Use or reproduction of materials protected by copyright beyond that allowed by fair use (Title 17, U.S.C. § 107) requires permission from the copyright owners. The use or reproduction of some materials may also be restricted by terms of University of California gift or purchase agreements, privacy and publicity rights, or trademark law. Responsibility for determining rights status and permissibility of any use or reproduction rests exclusively with the researcher. To learn more or make inquiries, please see our permissions policies (https://www.lib.berkeley.edu/about/permissions-policies).
