ParitoSVR: Parallel Iterated Optimizer for Support Vector Regression in the Primal

Regression problems on massive data sets are ubiquitous in many application domains including the Internet, earth and space sciences, and aviation. Support vector regression (SVR) is a popular technique for modeling the inputoutput relations of a set of variables under the added constraint of maximizing the margin, thereby leading to a very generalizable and regularized model. However, for a dataset with m training points, it is challenging to build SVR models due to the O(m) cost involved in building them. In this paper we propose ParitoSVR — a parallel iterated optimizer for Support Vector Regression in the primal that can be deployed over a network of machines, where each machine iteratively solves a small (sub-)problem based only on the data observed locally and these solutions are then combined to form the solution to the global problem. Experiments on real datasets demonstrate the accuracy and scalability of our algorithm. As a real application, we use ParitoSVR to detect flights having abnormal fuel consumption from a fleet-wide commercial aviation database.