Probabilistic Discriminative Kernel Classifiers for Multi-class Problems

摘要: Logistic regression is presumably the most popular representative of probabilistic discriminative classifiers. In this paper, a kernel variant logistic introduced as an iteratively re-weighted least-squares algorithm in kernel-induced feature spaces. This formulation allows us to apply highly efficient approximation methods that are capable dealing with large-scale problems. For multi-class problems, pairwise coupling procedure proposed. Pairwise for "kernelized" effectively overcomes conceptual and numerical problems standard