Exact Tensor Completion Beyond Isotropy and Invertibility

Li Ge, Lin Chen, Yudong Chen, Xue Jiang

TL;DR: We break the contraints of isotropy and self-adjointness, having established exact tensor completion guarantee with arbitrary linear transforms, and disclose why slim transforms outperform their square counterparts theoretically.

Abstract: 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 invertibility for the first time, 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, we theoretically disclose why slim transforms outperform their square counterparts, providing support for existing works on experimental excellence of slim transforms. Our model and analysis greatly enhance the flexibility of tensor completion, supported by extensive experimental results.

Code Dataset Promise: Yes

Code Dataset Url: https://github.com/vecevecev/Transformed_TNN

Format Confirmation: I agree that I have read and followed the formatting instructions for the camera ready version.

Submission Number: 2207