Multiclass Classification Using Support Vector Machines

In this thesis, we discuss different SVM methods for multiclass classification and introduce the Divide and Conquer Support Vector Machine (DCSVM) algorithm which relies on data sparsity in high dimensional space and performs a smart partitioning of the whole training data set into disjoint subsets that are easily separable. A single prediction performed between two partitions eliminates one or more classes in a single partition, leaving only a reduced number of candidate classes for subsequent steps. The algorithm continues recursively, reducing the number of classes at each step until a final binary decision is made between the last two classes left in the process. In the best case scenario, our algorithm makes a final decision between k classes in O(log2 k) decision steps and in the worst case scenario, DCSVM makes a final decision in k - 1 steps