A Linearly Convergent Linear-Time First-Order Algorithm for Support Vector Classification with a Core Set Result

We present a simple first-order approximation algorithm for the support vector classification problem. Given a pair of linearly separable data sets and epsilon is an element of(0, 1), the proposed algorithm computes a separating hyperplane whose margin is within a factor of (1-is an element of) of that of the maximum-margin separating hyperplane. We discuss how our algorithm can be extended to nonlinearly separable and inseparable data sets. The running time of our algorithm is linear in the number of data points and in 1/is an element of. In particular, the number of support vectors computed by the algorithm is bounded above by O(zeta/is an element of) for all sufficiently small is an element of > 0, where zeta is the square of the ratio of the distances between the farthest and closest pairs of points in the two data sets. Furthermore, we establish that our algorithm exhibits linear convergence. Our computational experiments, presented in the online supplement, reveal that the proposed algorithm performs quite well on standard data sets in comparison with other first-order algorithms. We adopt the real number model of computation in our analysis.