Fast Guaranteed Tensor Recovery with Adaptive Tensor Nuclear Norm

Authors: Jiangjun Peng, Hailin Wang, Xiangyong Cao, Shuang Xu

IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments demonstrate the effectiveness of the proposed method, showing improved accuracy and speed over existing approaches. Our code and supplementary material are available at https://github.com/ andrew-pengjj/adaptive_tensor_nuclear_norm.
Researcher Affiliation Academia 1 School of Mathematics and Statistics, Northwestern Polytechnical University, Xi an 710129, China 2 Shenzhen Research Institute of Northwestern Polytechnical University, Shenzhen 518057, China 3 School of Mathematics and Statistics, Xi an Jiaotong University, Xi an 710049, China 4 School of Computer Science and Technology, Xi an Jiaotong University, Xi an 710049, China
Pseudocode No Due to page limitations, the update procedures, detailed optimization steps and convergence guarantees are provided in the supplementary material.
Open Source Code Yes Our code and supplementary material are available at https://github.com/ andrew-pengjj/adaptive_tensor_nuclear_norm.
Open Datasets Yes The HSI tasks include the pavia U and WDC datasets, while the MSI consists of the Beans and Cloth datasets from the CAVE collection. The video surveillance data is sourced from the Li dataset, with detailed information available in the supplementary material. The newly added color video data includes four datasets: Akiyo, Foreman, Carphone, and News.
Dataset Splits No The paper mentions generating test samples by introducing random missing values or adding salt-and-pepper noise, but it does not specify explicit train/test/validation splits for any dataset (e.g., specific percentages or sample counts for training, validation, and testing).
Hardware Specification Yes All simulations were performed on a PC with an Intel Core i5-10600KF 4.10 GHz CPU, 32 GB RAM, and a Ge Force RTX 3080 GPU (10 GB).
Software Dependencies No The paper references the ADMM framework and mentions implementation details provided in supplementary material, but it does not list any specific software libraries, frameworks, or their version numbers used for implementation in the main text.
Experiment Setup Yes We consider n = 50 and two values of r3, i.e., r3 = 5, 20. We vary the sparsity ρsof E0 as [0.01 : 0.01 : 0.5], the missing ratio ρ of T0 as [0.01 : 0.02 : 0.99], and tubal rank of T0 as [1 : 1 : 50], respectively. For each combination of (R, ρs) and (R, ρ), we perform 10 test instances and declare a trial successful if the relative recovered error is less than 0.01. Based on Theorem 5, λ was set to 1/ p max{n1, n2} for all TRPCA tasks.