Rademacher Complexity Bounds for a Penalized Multi-class Semi-supervised Algorithm

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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:The Journal of artificial intelligence research Jg. 61; S. 761 - 786
Hauptverfasser: Maximov, Yury, Amini, Massih-Reza, Harchaoui, Zaid
Format: Journal Article
Sprache:Englisch
Veröffentlicht: San Francisco AI Access Foundation 01.01.2018
Schlagworte:
Algorithms
Artificial intelligence
Classifiers
Clustering
Complexity
Training
ISSN:1076-9757, 1076-9757, 1943-5037
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1076-9757
1076-9757
1943-5037
DOI:10.1613/jair.5638