yahoo/SparkADMM

The code in this repository provides a framework for solving arbitrary separable convex optimization problems with Alternating Direction Method of Multipliers (ADMM). Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers. The framework is built over Spark and is generic: to apply it to an arbitrary separable convex problem, a developer needs to implement only three functions (one that reads data from a file, one that evaluates the objective function, and one that solves a local optimization problem with an additional proximal penalty term). An example implementation of logistic regression is included in the code. Updated spark installation instructions can be found here.