Online learning techniques, such as Stochastic Gradient Descent (SGD), are powerful when applied to risk minimization and convex games on large problems. However, their sequential design prevents them from taking advantage of newer distributed frameworks such as Hadoop/YARN. In this session, we will introduce “Knitting Boar”, an open-source Java library for performing distributed online learning on a Hadoop cluster under YARN. We will give an overview of how Knitting Boar works and examine the lessons learned from YARN application construction.
The content will be similar to a talk given at Strata / Hadoop World in NYC:
If you want to seen a non-distributed example of SGD then please check out