A Class of Parallel Decomposition Algorithms for SVMs Training

Abstract

The training of Support Vector Machines may be a very difficult task when dealing with very large datasets. The memory requirement and the time consumption of the SVMs algorithms grow rapidly with the increase of the data. To overcome these drawbacks, we propose a parallel decomposition algorithmic scheme for SVMs training for which we prove global convergence under suitable conditions. We outline how these assumptions can be satisfied in practice and we suggest various specific implementations exploiting the adaptable structure of the algorithmic model.