Boosted Sparse and Low-Rank Tensor Regression

Abstract

We propose a sparse and low-rank tensor regression model to relate a univariate outcome to a feature tensor, in which each unit-rank tensor from the CP decomposition of the coefficient tensor is assumed to be sparse. This structure is both parsimonious and highly interpretable, as it implies that the outcome is related to the features through a few distinct pathways, each of which may only involve subsets of feature dimensions. We take a divide-and-conquer strategy to simplify the task into a set of sparse unit-rank tensor regression problems. To make the computation efficient and scalable, for the unit-rank tensor regression, we propose a stagewise estimation procedure to efficiently trace out its entire solution path. We show that as the step size goes to zero, the stagewise solution paths converge exactly to those of the corresponding regularized regression. The superior performance of our approach is demonstrated on various real-world and synthetic examples.

arXiv comment10 pages, 5 figures, NIPS 2018

Cited by in corpus (12)

• Tensor Regression Using Low-rank and Sparse Tucker Decompositions
• BrainNNExplainer: An Interpretable Graph Neural Network Framework for Brain Network based Disease Analysis
• Broadcasted Nonparametric Tensor Regression
• Multiplex Graph Networks for Multimodal Brain Network Analysis
• Statistically Guided Divide-and-Conquer for Sparse Factorization of Large Matrix
• Linear Tensor Projection Revealing Nonlinearity
• Sturm: Sparse Tubal-Regularized Multilinear Regression for fMRI
• Tensor Convolutional Sparse Coding with Low-Rank activations, an application to EEG analysis
• Generalized Co-sparse Factor Regression
• Sparse and Low-Rank High-Order Tensor Regression via Parallel Proximal Method
• Multivariate Convolutional Sparse Coding with Low Rank Tensor
• Fast and Scalable Estimator for Sparse and Unit-Rank Higher-Order Regression Models