Exact Tensor Completion Powered by Slim Transforms

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ge, Li, Chen, Lin, Chen, Yudong, Jiang, Xue
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929459646431232
author Ge, Li
Chen, Lin
Chen, Yudong
Jiang, Xue
author_facet Ge, Li
Chen, Lin
Chen, Yudong
Jiang, Xue
contents In this work, a tensor completion problem is studied, which aims to perfectly recover the tensor from partial observations. The existing theoretical guarantee requires the involved transform to be orthogonal, which hinders its applications. In this paper, jumping out of the constraints of isotropy and self-adjointness, the theoretical guarantee of exact tensor completion with arbitrary linear transforms is established by directly operating the tensors in the transform domain. With the enriched choices of transforms, a new analysis obtained by the proof discloses why slim transforms outperform their square counterparts from a theoretical level. Our model and proof greatly enhance the flexibility of tensor completion and extensive experiments validate the superiority of the proposed method.
format Preprint
id arxiv_https___arxiv_org_abs_2402_03468
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exact Tensor Completion Powered by Slim Transforms
Ge, Li
Chen, Lin
Chen, Yudong
Jiang, Xue
Machine Learning
Signal Processing
In this work, a tensor completion problem is studied, which aims to perfectly recover the tensor from partial observations. The existing theoretical guarantee requires the involved transform to be orthogonal, which hinders its applications. In this paper, jumping out of the constraints of isotropy and self-adjointness, the theoretical guarantee of exact tensor completion with arbitrary linear transforms is established by directly operating the tensors in the transform domain. With the enriched choices of transforms, a new analysis obtained by the proof discloses why slim transforms outperform their square counterparts from a theoretical level. Our model and proof greatly enhance the flexibility of tensor completion and extensive experiments validate the superiority of the proposed method.
title Exact Tensor Completion Powered by Slim Transforms
topic Machine Learning
Signal Processing
url https://arxiv.org/abs/2402.03468