Conference item icon

Conference item

Accelerated consensus via Min-Sum Splitting

Abstract:
We apply the Min-Sum message-passing protocol to solve the consensus problem in distributed optimization. We show that while the ordinary Min-Sum algorithm does not converge, a modified version of it known as Splitting yields convergence to the problem solution. We prove that a proper choice of the tuning parameters allows Min-Sum Splitting to yield subdiffusive accelerated convergence rates, matching the rates obtained by shift-register methods. The acceleration scheme embodied by Min-Sum Splitting for the consensus problem bears similarities with lifted Markov chains techniques and with multi-step first order methods in convex optimization.
Publication status:
Published
Peer review status:
Peer reviewed

Actions

Access Document

Files:

Authors

More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Statistics
Oxford college:
University College
Role:
Author


Publisher:
Curran Associates
Host title:
Advances in Neural Information Processing Systems 30: 31st Annual Conference on Neural Information Processing Systems (NIPS 2017)
Journal:
NIPS 2017 More from this journal
Volume:
30
Pages:
1375-1385
Publication date:
2018-06-01
Acceptance date:
2017-09-04
ISSN:
1049-5258
ISBN:
9781510860964


Pubs id:
pubs:729367
UUID:
uuid:56db55d5-7953-4b0d-a0c5-3ad435f6a8e7
Local pid:
pubs:729367
Source identifiers:
729367
Deposit date:
2017-11-03
ARK identifier:

Terms of use


Views and Downloads






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

TO TOP