AI Chat AI Image Generator AI Video Text to Speech

Coupled Tensor Completion via Low-rank Tensor Ring

01/09/2020

∙

by Huyan Huang, et al.

∙

∙

The coupled tensor decomposition aims to reveal the latent data structure which may share common factors. Using the recently proposed tensor ring decomposition, in this paper we propose a non-convex method by alternately optimizing the latent factors. We provide an excess risk bound for the proposed alternating minimization model, which shows the improvement in completion performance. The proposed algorithm is validated on synthetic data.

Huyan Huang
5 publications
Yipeng Liu
36 publications
Ce Zhu
48 publications

research

∙ 05/22/2018

Rank Minimization on Tensor Ring: A New Paradigm in Scalable Tensor Decomposition and Completion

In low-rank tensor completion tasks, due to the underlying multiple larg...

0 Longhao Yuan, et al. ∙

research

∙ 05/15/2017

Convex Coupled Matrix and Tensor Completion

We propose a set of convex low rank inducing norms for a coupled matrice...

0 Kishan Wimalawarne, et al. ∙

research

∙ 03/17/2023

Non-convex approaches for low-rank tensor completion under tubal sampling

Tensor completion is an important problem in modern data analysis. In th...

0 Zheng Tan, et al. ∙

research

∙ 03/12/2019

Tensor Grid Decomposition with Application to Tensor Completion

The recently prevalent tensor train (TT) and tensor ring (TR) decomposit...

0 Huyan Huang, et al. ∙

research

∙ 03/06/2017

Orthogonalized ALS: A Theoretically Principled Tensor Decomposition Algorithm for Practical Use

The popular Alternating Least Squares (ALS) algorithm for tensor decompo...

0 Vatsal Sharan, et al. ∙

research

∙ 03/08/2019

Tensor Completion using Balanced Unfolding of Low-Rank Tensor Ring

Tensor completion aims to recover a multi-dimensional array from its inc...

0 Huyan Huang, et al. ∙

research

∙ 01/19/2022

Coupled Support Tensor Machine Classification for Multimodal Neuroimaging Data

Multimodal data arise in various applications where information about th...

0 Li Peide, et al. ∙