Sparse Logistic Tensor Decomposition for Binary Data

Abstract

Tensor data are increasingly available in many application domains. We develop several tensor decomposition methods for binary tensor data. Different from classical tensor decompositions for continuous-valued data with squared error loss, we formulate logistic tensor decompositions for binary data with a Bernoulli likelihood. To enhance the interpretability of estimated factors and improve their stability further, we propose sparse formulations of logistic tensor decomposition by considering ${\ell }_1$-norm and ${\ell }_0$-norm regularized likelihood. To handle the resulting optimization problems, we develop computational algorithms which combine the strengths of tensor power method and majorization-minimization (MM) algorithm. Through simulation studies, we demonstrate the utility of our methods in analysis of binary tensor data. To illustrate the effectiveness of the proposed methods, we analyze a dataset concerning nations and their political relations and perform co-clustering of estimated factors to find associations between the nations and political relations.

References in corpus (6)

• Scalable Tensor Factorizations for Incomplete Data
• Tensor Regression with Applications in Neuroimaging Data Analysis
• Truncated Power Method for Sparse Eigenvalue Problems
• Generalized Canonical Polyadic Tensor Decomposition
• Dimensionality Reduction for Binary Data through the Projection of Natural Parameters
• Sparse logistic principal components analysis for binary data