-

 

 

 




Optimization Online





 

Balancing Communication and Computation in Distributed Optimization

Albert S Berahas (albertberahas***at***u.northwestern.edu)
Raghu Bollapragada (raghu.bollapragada***at***u.northwestern.edu)
Nitish Shirish Keskar (keskar.nitish***at***u.northwestern.edu)
Ermin Wei (ermin.wei***at***northwestern.edu)

Abstract: Methods for distributed optimization have received significant attention in recent years owing to their wide applicability in various domains including machine learning, robotics and sensor networks. A distributed optimization method typically consists of two key components: communication and computation. More specifically, at every iteration (or every several iterations) of a distributed algorithm, each node in the network requires some form of information exchange with its neighboring nodes (communication) and the computation step related to a (sub)-gradient (computation). The standard way of judging an algorithm via only the number of iterations overlooks the complexity associated with each iteration. Moreover, various applications deploying distributed methods may prefer a different composition of communication and computation. Motivated by this discrepancy, in this work we propose an adaptive cost framework which adjusts the cost measure depending on the features of various applications. We present a flexible algorithmic framework, where communication and computation steps are explicitly decomposed to enable algorithm customization for various applications. We apply this framework to the well-known distributed gradient descent (DGD) method, and show that the customized algorithms, which we call DGD$^t$, NEAR-DGD$^t$ and NEAR-DGD$^+$, compare favorably to their base algorithms, both theoretically and empirically. The proposed NEAR-DGD$^+$ algorithm is an exact first-order method where the communication and computation steps are nested, and when the number of communication steps is adaptively increased, the method converges to the optimal solution. We test the performance and illustrate the flexibility of the methods, as well as practical variants, on quadratic functions and classification problems that arise in machine learning, in terms of iterations, gradient evaluations, communications and the proposed cost framework.

Keywords: Distributed Optimization, Consensus, Communication, Computation, Cost Framework.

Category 1: Convex and Nonsmooth Optimization (Convex Optimization )

Category 2: Network Optimization

Category 3: Infinite Dimensional Optimization (Distributed Control )

Citation:

Download: [PDF]

Entry Submitted: 10/02/2017
Entry Accepted: 10/02/2017
Entry Last Modified: 10/06/2017

Modify/Update this entry


  Visitors Authors More about us Links
  Subscribe, Unsubscribe
Digest Archive
Search, Browse the Repository

 

Submit
Update
Policies
Coordinator's Board
Classification Scheme
Credits
Give us feedback
Optimization Journals, Sites, Societies
Mathematical Optimization Society