Allerton 2015 Paper Abstract


Paper ThB2.1

Li, Songze (USC), Maddah-ali, Mohammad Ali (Bell Labs Alcatel-Lucent), Avestimehr, Salman (USC)

Coded MapReduce

Scheduled for presentation during the Invited Session "Information Theory and Applications" (ThB2), Thursday, October 1, 2015, 10:30−10:50, Solarium

53rd Annual Allerton Conference on Communication, Control, and Computing, Sept 29-Oct 2, 2015, Allerton Park and Retreat Center, Monticello, IL, USA

This information is tentative and subject to change. Compiled on December 5, 2021

Keywords Information Theory, Distributed Computation on Networks


MapReduce is a commonly used framework for executing data-intensive tasks on distributed server clusters. We present "Coded MapReduce", a new framework that enables and exploits a particular form of coding to significantly reduce the inter-server communication load of MapReduce. In particular, Coded MapReduce exploits the repetitive mapping of data blocks at different servers to create coded multicasting opportunities in the shuffling phase, cutting down the total communication load by a multiplicative factor that grows linearly with the number of servers in the cluster. We also analyze the tradeoff between the "computation load" and the "communication load" of the Coded MapReduce.



All Content © PaperCept, Inc..

This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2021 PaperCept, Inc.
Page generated 2021-12-05  10:23:12 PST  Terms of use