Year: 2025
Type: preprint
Abstract: This paper develops two efficient iterative methods for solving tensor equations under the T-product framework. For T-symmetric positive definite tensor equations of the form $\mathcal{C} \star \mathcal{X} = \mathcal{D}$, we propose a conjugate-gradient-type algorithm that generates orthogonal residual and $\mathcal{C}$-orthogonal direction sequences, ensuring convergence within a finite number of steps. For general consistent tensor equations, we extend the method using a normal-equation transformation, and further adapt it to handle inconsistent systems by solving a least-squares minimization problem. Key advantages include direct tensor-based computations without explicit matrix expansion, rigorous finite-step convergence proofs, and the ability to obtain minimal Frobenius norm solutions. Numerical experiments on synthetic data, benchmark images, and video sequences demonstrate that the proposed algorithms achieve high precision with low computational time, confirming their practicality for large-scale multidimensional problems.
Source: arXiv (Cornell University)
Institutions: Innopolis University, Vali Asr University of Rafsanjan
Language: English
Subfield: Computational Mathematics
Field: Mathematics
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4416375346
Cites:
Cited by:
Related to: