Rademacher Complexity Bounds for a Penalized Multi-class Semi-supervised Algorithm (Extended Abstract)
Rademacher Complexity Bounds for a Penalized Multi-class Semi-supervised Algorithm (Extended Abstract)
Yury Maximov, Massih-Reza Amini, Zaid Harchaoui
Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
Journal track. Pages 5637-5641.
https://doi.org/10.24963/ijcai.2018/800
We propose Rademacher complexity bounds for multi-class classifiers trained with a two-step semi-supervised model. In the first step, the algorithm partitions the partially labeled data and then identifies dense clusters containing k predominant classes using the labeled training examples such that the proportion of their non-predominant classes is below a fixed threshold stands for clustering consistency. In the second step, a classifier is trained by minimizing a margin empirical loss over the labeled training set and a penalization term measuring the disability of the learner to predict the k predominant classes of the identified clusters. The resulting data-dependent generalization error bound involves the margin distribution of the classifier, the stability of the clustering technique used in the first step and Rademacher complexity terms corresponding to partially labeled training data. Our theoretical result exhibit convergence rates extending those proposed in the literature for the binary case, and experimental results on different multi-class classification problems show empirical evidence that supports the theory.
Keywords:
Machine Learning: Classification
Machine Learning: Clustering
Machine Learning: Machine Learning
Machine Learning: Semi-Supervised Learning