Theoretical and Experimental Analyses of Tensor-Based Regression and Classification
arXiv:1509.01770
Abstract
We theoretically and experimentally investigate tensor-based regression and classification. Our focus is regularization with various tensor norms, including the overlapped trace norm, the latent trace norm, and the scaled latent trace norm. We first give dual optimization methods using the alternating direction method of multipliers, which is computationally efficient when the number of training samples is moderate. We then theoretically derive an excess risk bound for each tensor norm and clarify their behavior. Finally, we perform extensive experiments using simulated and real data and demonstrate the superiority of tensor-based learning methods over vector- and matrix-based learning methods.
References in corpus (6)
- Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
- Tensor Regression with Applications in Neuroimaging Data Analysis
- Regularized Matrix Regression
- Estimation of low-rank tensors via convex optimization
- Convex Tensor Decomposition via Structured Schatten Norm Regularization
- Super-Linear Convergence of Dual Augmented-Lagrangian Algorithm for Sparsity Regularized Estimation