A Deterministic Information Bottleneck Method for Clustering Mixed-Type
Data
A Deterministic Information Bottleneck Method for Clustering Mixed-Type
Data
In this paper, we present an information-theoretic method for clustering mixed-type data, that is, data consisting of both continuous and categorical variables. The method is a variant of the Deterministic Information Bottleneck algorithm which optimally compresses the data while retaining relevant information about the underlying structure. We compare the performance …