Estimation of Gaussian Bi-Clusters with General Block-Diagonal Covariance Matrix and Applications

TL;DR

This paper introduces a flexible Gaussian mixture model for bi-clustering with block-diagonal covariance matrices, offering comparable accuracy to existing methods but with greater flexibility and reduced computational time, demonstrated in bioinformatics and topic modeling.

Contribution

The paper proposes a novel Gaussian mixture model for bi-clustering that allows for a more flexible block-diagonal covariance structure, improving efficiency and applicability.

Findings

Clustering accuracy is comparable to existing methods.

The proposed approach has substantially lower computational time.

Effective in bioinformatics and topic modeling applications.

Abstract

Bi-clustering is a technique that allows for the simultaneous clustering of observations and features in a dataset. This technique is often used in bioinformatics, text mining, and time series analysis. An important advantage of biclustering algorithm is the ability to uncover multiple ``views'' (i.e., through rows and column groupings) in the data. Several Gaussian mixture model based biclustering approach currently exist in the literature. However, they impose severe restrictions on the structure of the covariance matrix. Here, we propose a Gaussian mixture model-based bi-clustering approach that provides a more flexible block-diagonal covariance structure. We show that the clustering accuracy of the proposed model is comparable to other known techniques but our approach provides a more flexible covariance structure and has substantially lower computational time. We demonstrate the application of the proposed model in bioinformatics and topic modelling.