Scaled coupled norms and coupled higher-order tensor completion

No Thumbnail Available

Access rights

openAccess

URL

Journal Title

Journal ISSN

Volume Title

A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Date

2020-02-01

Major/Subject

Mcode

Degree programme

Language

en

Pages

38
447-484

Series

Neural Computation, Volume 32, issue 2

Abstract

Recently, a set of tensor norms known as coupled norms has been proposed as a convex solution to coupled tensor completion. Coupled norms have been designed by combining low-rank inducing tensor norms with the matrix trace norm. Though coupled norms have shown good performances, they have two major limitations: they do not have a method to control the regularization of coupled modes and uncoupled modes, and they are not optimal for couplings among higher-order tensors. In this letter, we propose a method that scales the regularization of coupled components against uncoupled components to properly induce the low-rankness on the coupled mode. We also propose coupled norms for higher-order tensors by combining the square norm to coupled norms. Using the excess risk-bound analysis, we demonstrate that our proposed methods lead to lower risk bounds compared to existing coupled norms. We demonstrate the robustness of our methods through simulation and real-data experiments.

Description

Keywords

Other note

Citation

Wimalawarne, K, Yamada, M & Mamitsuka, H 2020, ' Scaled coupled norms and coupled higher-order tensor completion ', Neural Computation, vol. 32, no. 2, pp. 447-484 . https://doi.org/10.1162/neco_a_01254