Noisy tensor completion via low-rank tensor ring
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 …
predict missing entries from partial observations. However, existing methods often make the …
Imbalanced low-rank tensor completion via latent matrix factorization
Tensor completion has been widely used in computer vision and machine learning. Most
existing tensor completion methods empirically assume the intrinsic tensor is simultaneous …
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 …
completion due to its powerful representation ability of high-order tensors. However, most of …
Robust tensor decomposition via orientation invariant tubal nuclear norms
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 …
outliers and dense noises, robust tensor decomposition (RTD) serves as a powerful pre …
Guaranteed nonconvex factorization approach for tensor train recovery
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 …
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
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 …
edge caching and hyper-spectral imaging. In wireless edge caching, the dynamic and …
Beyond unfolding: Exact recovery of latent convex tensor decomposition under reshuffling
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 …
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 …
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 …
generation networks, where the content is cached in advance at base stations to serve …