Multi-Tensor Network Representation for High-Order Tensor Completion

• Published in: arXiv.org
• Main Authors: Nie, Chang, Wang, Huan, Lai, Zhihui
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 21.09.2021
• Subjects: Algorithms; Data recovery; Decomposition; Error analysis; Machine learning; Mathematical analysis; Optimization; Representations; Tensors; Topology

This work studies the problem of high-dimensional data (referred to as tensors) completion from partially observed samplings. We consider that a tensor is a superposition of multiple low-rank components. In particular, each component can be represented as multilinear connections over several latent...