Regularized Gaussian Mixture Model for High-Dimensional Clustering

Finding low-dimensional representation of high-dimensional data sets is an important task in various applications. The fact that data sets often contain clusters embedded in different subspaces poses barrier to this task. Driven by the need in methods that enable clustering and finding each cluster's intrinsic subspace simultaneously, in this paper, we propose a regularized Gaussian mixture model (GMM) for clustering. Despite the advantages of GMM, such as its probabilistic interpretation and robustness against observation noise, traditional maximum-likelihood estimation for GMMs shows disappointing performance in high-dimensional setting. The proposed regularization method finds low-dimensional representations of the component covariance matrices, resulting in better estimation of local feature correlations. The regularization problem can be incorporated in the expectation maximization algorithm for maximizing the likelihood function of a GMM, with the M-step modified to incorporate the regularization. The M-step involves a determinant maximization problem, which can be solved efficiently. The performance of the proposed method is demonstrated using several simulated data sets. We also illustrate the potential value of the proposed method in applications using four real data sets.