Rademacher complexity bounds for a penalized multi-class semi-supervised algorithm

Yury Maximov, Massih Reza Amini, Zaid Harchaoui

    Research output: Contribution to journalArticlepeer-review

    8 Citations (Scopus)


    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 κ 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 κ 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.

    Original languageEnglish
    Pages (from-to)761-786
    Number of pages26
    JournalJournal of Artificial Intelligence Research
    Publication statusPublished - 1 Apr 2018


    Dive into the research topics of 'Rademacher complexity bounds for a penalized multi-class semi-supervised algorithm'. Together they form a unique fingerprint.

    Cite this