BudgetedSVM: a toolbox for scalable SVM approximations

Abstract

We present BudgetedSVM, an open-source C++ toolbox comprising highly-optimized implemen-tations of recently proposed algorithms for scalable training of Support Vector Machine (SVM) ap-proximators: Adaptive Multi-hyperplane Machines, Low-rank Linearization SVM, and Budgeted Stochastic Gradient Descent. BudgetedSVM trains models with accuracy comparable to LibSVM in time comparable to LibLinear, solving non-linear problems with millions of high-dimensional examples within minutes on a regular computer. We provide command-line and Matlab interfaces to BudgetedSVM, an efficient API for handling large-scale, high-dimensional data sets, as well as detailed documentation to help developers use and further extend the toolbox.