Noisy tensor completion via low-rank tensor ring

Y Qiu, G Zhou, Q Zhao, S Xie - IEEE Transactions on Neural …, 2022 - ieeexplore.ieee.org
Tensor completion is a fundamental tool for incomplete data analysis, where the goal is to
predict missing entries from partial observations. However, existing methods often make the …

Imbalanced low-rank tensor completion via latent matrix factorization

Y Qiu, G Zhou, J Zeng, Q Zhao, S Xie - Neural Networks, 2022 - Elsevier
Tensor completion has been widely used in computer vision and machine learning. Most
existing tensor completion methods empirically assume the intrinsic tensor is simultaneous …

Robust to rank selection: Low-rank sparse tensor-ring completion

J Yu, G Zhou, W Sun, S Xie - IEEE Transactions on Neural …, 2021 - ieeexplore.ieee.org
Tensor-ring (TR) decomposition was recently studied and applied for low-rank tensor
completion due to its powerful representation ability of high-order tensors. However, most of …

Robust tensor decomposition via orientation invariant tubal nuclear norms

A Wang, QB Zhao, Z Jin, C Li, GX Zhou - Science China Technological …, 2022 - Springer
Aiming at recovering an unknown tensor (ie, multi-way array) corrupted by both sparse
outliers and dense noises, robust tensor decomposition (RTD) serves as a powerful pre …

Guaranteed nonconvex factorization approach for tensor train recovery

Z Qin, MB Wakin, Z Zhu - arXiv preprint arXiv:2401.02592, 2024 - arxiv.org
In this paper, we provide the first convergence guarantee for the factorization approach.
Specifically, to avoid the scaling ambiguity and to facilitate theoretical analysis, we optimize …

Tensor Completion Algorithm and its Applications to Wireless Edge Caching and Hyper-Spectral Imaging

N Garg, Z Liu, T Ratnarajah - IEEE Access, 2024 - ieeexplore.ieee.org
This paper presents a lightweight tensor completion algorithm with applications in wireless
edge caching and hyper-spectral imaging. In wireless edge caching, the dynamic and …

Beyond unfolding: Exact recovery of latent convex tensor decomposition under reshuffling

C Li, ME Khan, Z Sun, G Niu, B Han, S Xie… - Proceedings of the AAAI …, 2020 - aaai.org
Exact recovery of tensor decomposition (TD) methods is a desirable property in both
unsupervised learning and scientific data analysis. The numerical defects of TD methods …

An efficient tensor completion method via new latent nuclear norm

J Yu, W Sun, Y Qiu, Y Huang - IEEE Access, 2020 - ieeexplore.ieee.org
In tensor completion, the latent nuclear norm is commonly used to induce low-rank structure,
while substantially failing to capture the global information due to the utilization of …

Low-complexity Rank-Efficient Tensor Completion For Prediction And Online Wireless Edge Caching

N Garg, T Ratnarajah - arXiv preprint arXiv:2101.12146, 2021 - arxiv.org
Wireless edge caching is a popular strategy to avoid backhaul congestion in the next
generation networks, where the content is cached in advance at base stations to serve …