Minimum Conditional Entropy Clustering: A Discriminative Framework for Clustering

In this paper, we introduce an assumption which makes it possible to extend the learning ability of discriminative model to unsupervised setting. We propose an informationtheoretic framework as an implementation of the low-density separation assumption. The proposed framework provides a unified perspective of Maximum Margin Clustering (MMC), Discriminative k-means, Spectral Clustering and Unsupervised Renyi's Entropy Analysis and also leads to a novel and efficient algorithm, Accelerated Maximum Relative Margin Clustering (ARMC), which maximizes the margin while considering the spread of projections and affine invariance. Experimental results show that the proposed discriminative unsupervised learning method is more efficient in utilizing data and achieves the state-ofthe-art or even better performance compared with mainstream clustering methods.

• Type: Journal
• Year: 2010
• Where: JMLR
• Authors: Bo Dai, Baogang Hu
• Keywords: Discriminative Unsupervised Learning, JMLR 2010, Low-density Separation Assumption, Mainstream Clustering Methods