Anomaly Detection in Map-Reduce
October 20, 2016
10:50 am - 11:10 am
GRB 330 A
Track:
Artificial Intelligence
Type: Presentation
Level:
Beginner/Intermediate
Map-Reduce systems have built-in fault-tolerance that allow jobs to run to completion even in the presence of certain faults. However, these jobs can experience severe performance penalties under faulty conditions. In order to mitigate these penalties, we propose an anomaly detection method based on sparse-coding to anticipate a faulty node and illustrate its efficacy through experimental results.
Speaker(s)
, ContainerX Inc. |