Type
Conference PaperAuthors
Loizou, NicolasRichtarik, Peter

KAUST Department
Computer Science ProgramComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
KAUST, University of Edinburgh, MIPT, , , Saudi Arabia
Date
2019-03-01Online Publication Date
2019-03-01Print Publication Date
2018-10Permanent link to this record
http://hdl.handle.net/10754/631783
Metadata
Show full item recordAbstract
In this paper we show how the stochastic heavy ball method (SHB)-a popular method for solving stochastic convex and non-convex optimization problems-operates as a randomized gossip algorithm. In particular, we focus on two special cases of SHB: the Randomized Kaczmarz method with momentum and its block variant. Building upon a recent framework for the design and analysis of randomized gossip algorithms [20] we interpret the distributed nature of the proposed methods. We present novel protocols for solving the average consensus problem where in each step all nodes of the network update their values but only a subset of them exchange their private values. Numerical experiments on popular wireless sensor networks showing the benefits of our protocols are also presented.Citation
Loizou N, Richtarik P (2018) Accelerated Gossip via Stochastic Heavy Ball Method. 2018 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton). Available: http://dx.doi.org/10.1109/ALLERTON.2018.8636082.Conference/Event name
56th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2018Additional Links
https://ieeexplore.ieee.org/document/8636082ae974a485f413a2113503eed53cd6c53
10.1109/ALLERTON.2018.8636082