Successive Approximation Coding for Distributed Matrix Multiplication

01/10/2022
by   Shahrzad Kiani, et al.
0

Coded distributed computing was recently introduced to mitigate the effect of stragglers on distributed computing. This paper combines ideas of approximate computing with coded computing to further accelerate computation. We propose successive approximation coding (SAC) techniques that realize a tradeoff between accuracy and speed, allowing the distributed computing system to produce approximations that increase in accuracy over time. If a sufficient number of compute nodes finish their tasks, SAC exactly recovers the desired computation. We theoretically provide design guidelines for our SAC techniques, and numerically show that SAC achieves a better accuracy-speed tradeoff in comparison with previous methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/16/2019

Random Sampling for Distributed Coded Matrix Multiplication

Matrix multiplication is a fundamental building block for large scale co...
research
04/15/2019

Distributed Matrix Multiplication Using Speed Adaptive Coding

While performing distributed computations in today's cloud-based platfor...
research
01/23/2019

A Fundamental Storage-Communication Tradeoff in Distributed Computing with Straggling Nodes

The optimal storage-computation tradeoff is characterized for a MapReduc...
research
09/17/2020

Berrut Approximated Coded Computing: Straggler Resistance Beyond Polynomial Computing

One of the major challenges in using distributed learning to train compl...
research
11/17/2017

Approximate Gradient Coding via Sparse Random Graphs

Distributed algorithms are often beset by the straggler effect, where th...
research
10/24/2017

A Sequential Approximation Framework for Coded Distributed Optimization

Building on the previous work of Lee et al. and Ferdinand et al. on code...
research
07/20/2019

Hierarchical Coded Matrix Multiplication

Slow working nodes, known as stragglers, can greatly reduce the speed of...

Please sign up or login with your details

Forgot password? Click here to reset