Joint Tensor Factorization and Outlying Slab Suppression with Applications

Abstract

We consider factoring low-rank tensors in the presence of outlying slabs. This problem is important in practice, because data collected in many real-world applications, such as speech, fluorescence, and some social network data, fit this paradigm. Prior work tackles this problem by iteratively selecting a fixed number of slabs and fitting, a procedure which may not converge. We formulate this problem from a group-sparsity promoting point of view, and propose an alternating optimization framework to handle the corresponding ${\ell }_p$ ($0<p\le 1$) minimization-based low-rank tensor factorization problem. The proposed algorithm features a similar per-iteration complexity as the plain trilinear alternating least squares (TALS) algorithm. Convergence of the proposed algorithm is also easy to analyze under the framework of alternating optimization and its variants. In addition, regularization and constraints can be easily incorporated to make use of \emph{a priori} information on the latent loading factors. Simulations and real data experiments on blind speech separation, fluorescence data analysis, and social network mining are used to showcase the effectiveness of the proposed algorithm.

References in corpus (1)

• Robust PCA via Outlier Pursuit

Cited by in corpus (18)

• Tensor Decomposition for Signal Processing and Machine Learning
• A Flexible and Efficient Algorithmic Framework for Constrained Matrix and Tensor Factorization
• Robust Volume Minimization-Based Matrix Factorization for Remote Sensing and Document Clustering
• Spectrum Cartography via Coupled Block-Term Tensor Decomposition
• Semiblind Hyperspectral Unmixing in the Presence of Spectral Library Mismatches
• Hyperspectral Super-Resolution via Interpretable Block-Term Tensor Modeling
• Fast Low-Rank Bayesian Matrix Completion with Hierarchical Gaussian Prior Models
• Tensors, Learning, and 'Kolmogorov Extension' for Finite-alphabet Random Vectors
• Computing Large-Scale Matrix and Tensor Decomposition with Structured Factors: A Unified Nonconvex Optimization Perspective
• An Iterative Reweighted Method for Tucker Decomposition of Incomplete Multiway Tensors
• A Flexible Optimization Framework for Regularized Matrix-Tensor Factorizations with Linear Couplings
• The Exact Solution to Rank-1 L1-norm TUCKER2 Decomposition
• Inexact Alternating Optimization for Phase Retrieval In the Presence of Outliers
• Provable Online CP/PARAFAC Decomposition of a Structured Tensor via Dictionary Learning
• Block-Randomized Stochastic Proximal Gradient for Low-Rank Tensor Factorization
• Multi-Stage Network Embedding for Exploring Heterogeneous Edges
• Hanson-Wright Inequality for Random Tensors under Einstein Product
• Crowdsourcing via Annotator Co-occurrence Imputation and Provable Symmetric Nonnegative Matrix Factorization