Algebraic multigrid support vector machines
This work addresses a computational bottleneck for practitioners using support vector machines on large or imbalanced datasets, though it appears incremental as it builds on existing multigrid ideas.
The authors tackled the computational expense of training support vector machines on large-scale datasets by introducing a fast multilevel framework inspired by algebraic multigrid, achieving significant speed improvements without quality loss, particularly beneficial for imbalanced sets.
The support vector machine is a flexible optimization-based technique widely used for classification problems. In practice, its training part becomes computationally expensive on large-scale data sets because of such reasons as the complexity and number of iterations in parameter fitting methods, underlying optimization solvers, and nonlinearity of kernels. We introduce a fast multilevel framework for solving support vector machine models that is inspired by the algebraic multigrid. Significant improvement in the running has been achieved without any loss in the quality. The proposed technique is highly beneficial on imbalanced sets. We demonstrate computational results on publicly available and industrial data sets.