BudgetedSVM: a toolbox for scalable SVM approximations. (English) Zbl 1317.68153

Djuric, Nemanja; Lan, Liang; Vucetic, Slobodan; Wang, Zhuang

J. Mach. Learn. Res. 14, 3813-3817 (2013).

Summary: We present BudgetedSVM, an open-source C++ toolbox comprising highly-optimized implementations of recently proposed algorithms for scalable training of Support Vector Machine (SVM) approximators: 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.

MSC:

68T05	Learning and adaptive systems in artificial intelligence
62-04	Software, source code, etc. for problems pertaining to statistics
68-04	Software, source code, etc. for problems pertaining to computer science
62H30	Classification and discrimination; cluster analysis (statistical aspects)

Keywords:

nonlinear classification; large-scale learning; SVM; machine learning toolbox

Software:

Pegasos; MSVMpack; Matlab; LIBLINEAR; LIBSVM; BudgetedSVM