TY - GEN
T1 - Running MAP inference on million node graphical models
T2 - 15th IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing, CCGrid 2015
AU - Jin, Chen
AU - Fu, Qiang
AU - Wang, Huahua
AU - Hendrix, William
AU - Chen, Zhengzhang
AU - Agrawal, Ankit
AU - Banerjee, Arindam
AU - Choudhary, Alok
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/7/7
Y1 - 2015/7/7
N2 - An important problem in discrete graphical models is the maximum a posterior (MAP) inference problem. Recent research has been focusing on the development of parallel MAP inference algorithm, which scales to graphical models of millions of nodes. In this paper, we introduce a parallel implementation of the recently proposed Bethe-ADMM algorithm using Message Passing Interface (MPI), which allows us to fully utilize the computing power provided by the modern supercomputers with thousands of cores. Experimental results demonstrate that for a broad class of problems, our parallel implementation of Bethe-ADMM scales almost linearly even with thousands of cores.
AB - An important problem in discrete graphical models is the maximum a posterior (MAP) inference problem. Recent research has been focusing on the development of parallel MAP inference algorithm, which scales to graphical models of millions of nodes. In this paper, we introduce a parallel implementation of the recently proposed Bethe-ADMM algorithm using Message Passing Interface (MPI), which allows us to fully utilize the computing power provided by the modern supercomputers with thousands of cores. Experimental results demonstrate that for a broad class of problems, our parallel implementation of Bethe-ADMM scales almost linearly even with thousands of cores.
KW - Alternating direction method of multipliers
KW - Markov random field
KW - Maximum a posteriori inference
KW - Message passing interface
UR - http://www.scopus.com/inward/record.url?scp=84941248016&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84941248016&partnerID=8YFLogxK
U2 - 10.1109/CCGrid.2015.35
DO - 10.1109/CCGrid.2015.35
M3 - Conference contribution
AN - SCOPUS:84941248016
T3 - Proceedings - 2015 IEEE/ACM 15th International Symposium on Cluster, Cloud, and Grid Computing, CCGrid 2015
SP - 565
EP - 575
BT - Proceedings - 2015 IEEE/ACM 15th International Symposium on Cluster, Cloud, and Grid Computing, CCGrid 2015
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 4 May 2015 through 7 May 2015
ER -