Ling Liu's SC13 paper "Large Graph Processing Without the Overhead" featured by HPCwire.
Another list highlighting Open Source Software Releases.
Second GraphLab workshop should be even bigger than the first! GraphLab is a new programming framework for graph-style data analytics.
Distributed Delayed Proximal Gradient Methods
Workshop on OPT2013: Optimization for Machine Learning, with NIPS’13, December 2013.
Mu Li*, David G. Andersen* and Alexander Smola*^
*Carnegie Mellon University
^Google Strategic Technologies
We analyze distributed optimization algorithms where parts of data and variables are distributed over several machines and synchronization occurs asynchronously. We prove convergence for the general case of a nonconvex objective plus a convex and possibly nonsmooth penalty. We demonstrate two challenging applications, l1- regularized logistic regression and reconstruction ICA, and present experiments on real datasets with billions of variables using both CPUs and GPUs.
FULL PAPER: pdf