We propose an efficient and scalable robust high-order tensor recovery method solving a double nonconvex optimization with convergence guarantees.

Experiments on both synthetic and real tensor da- ta demonstrate that the proposed algorithm reconstructs the low-rank structures embedded in high-order tensors ...

Finally, we propose an efficient and scalable robust high-order tensor recovery method solving a double noncon-vex optimization with convergence guarantees.

May 19, 2023 · In this article, two efficient low-rank tensor approximation approaches fusing randomized techniques are first devised under the order-d (d >= 3) T-SVD ...

We develop a novel non-convex tensor pseudo-norm to replace the weighted sum of the tensor nuclear norm as a tighter rank approximation.

Apr 10, 2024 · Nevertheless, these methods involve the T-SVD based low-rank approximation, which suffers from high computational costs when dealing with large- ...

Apr 21, 2024 · Nevertheless, these methods involve the T-SVD based low-rank approximation, which suffers from high computational costs when dealing with large- ...

The latest tensor recovery methods based on tensor Singular Value Decomposition (t-SVD) mainly utilize the tensor nuclear norm (TNN) as a convex surrogate ...

This paper proposes tailored optimization algorithms with global convergence guarantees for solving both the constrained and the Lagrangian formulations of ...

Feb 1, 2023 · This paper considers the least squares loss minimization problem regularized by tensor average rank and zero norm, to decompose the noisy observation into a ...