Theoretical and experimental analyses of tensor-based regression and classification

DOI10.1162/NECO_A_00815zbMATH Open1418.62259arXiv1509.01770WikidataQ39987672 ScholiaQ39987672MaRDI QIDQ5380415FDOQ5380415

Kishan Wimalawarne, Masashi Sugiyama, Ryota Tomioka

Publication date: 4 June 2019

Published in: Neural Computation (Search for Journal in Brave)

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.

Full work available at URL: https://arxiv.org/abs/1509.01770

Recommendations

• Regularized high dimension low tubal-rank tensor regression
• Learning with tensors: a framework based on convex optimization and spectral regularization
• Convex regularization for high-dimensional multiresponse tensor regression
• Bayesian tensor regression
• Least square support tensor regression machine based on submatrix of the tensor

zbMATH Keywords

classificationtensor-based regression

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) General nonlinear regression (62J02)

Cites Work

• Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers
• A dual algorithm for the solution of nonlinear variational problems via finite element approximation
• Regularization and Variable Selection Via the Elastic Net
• Robust principal component analysis?
• A Singular Value Thresholding Algorithm for Matrix Completion
• Tensor Decompositions and Applications
• Regularized Matrix Regression
• Tensor Regression with Applications in Neuroimaging Data Analysis
• Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
• Title not available (Why is that?)
• Tensor completion and low-n-rank tensor recovery via convex optimization
• Learning with tensors: a framework based on convex optimization and spectral regularization
• Title not available (Why is that?)

Cited In (8)

• Gradient-based optimization for regression in the functional tensor-train format
• A Simple and Efficient Tensor Calculus for Machine Learning
• Convex Coupled Matrix and Tensor Completion
• A low-rank support tensor machine for multi-classification
• Tensor-on-Tensor Regression
• Multiway Sparse Distance Weighted Discrimination
• Title not available (Why is that?)
• Covariate-Adjusted Tensor Classification in High-Dimensions

This page was built for publication: Theoretical and experimental analyses of tensor-based regression and classification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5380415)