University of Cambridge > Talks.cam > Statistics > Accelerated Consensus via Min-Sum Splitting

Accelerated Consensus via Min-Sum Splitting

Add to your list(s) Download to your calendar using vCal

  • UserPatrick Rebeschini (Oxford)
  • ClockFriday 10 November 2017, 16:00-17:00
  • HouseMR12.

If you have a question about this talk, please contact Quentin Berthet.

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. (Joint work with Sekhar Tatikonda, based on arxiv.org/abs/1706.03807, at NIPS 2017 )

This talk is part of the Statistics series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2017 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity