Conflict Graphs for Parallel Stochastic Gradient Descent

We present various methods for inducing a conflict graph in order to effectively parallelize Pegasos. Pegasos is a stochastic sub-gradient descent algorithm for solving the Support Vector Machine (SVM) optimization problem [3]. In particular, we introduce a binary treebased conflict graph that matches convergence of a wellknown parallel implementation of stochastic gradient descent, know as HOGWILD!, while speeding up training time. We measure these results on a real-world dataset in a binary classification setting. This allows us to run various experiments to compare iterations between Parallel Pegasos and traditional Pegasos in order to effectively measure classification accuracy.