Exponential-Family Tensor Completion via Nonconvex Dual Total-Variation Regularization
IEEE Transactions on Signal Processing · 2026 · 74 · 3346-3361
DOI: 10.1109/tsp.2026.3716059 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Signal Processing, 2026. Verfasst von Wenfei Cao und 4 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
With the emergence of various tensor data, tensor completion from partial measurements has attracted widespread attention in data science and signal processing. Total Variation (TV) has been widely used as an effective regularization technique for tensor completion; however, theoretical studies on TV regularization in this context remain limited. In this work, we present a rigorous theoretical analysis of TV regularization for tensor completion. Specifically, we consider tensor completion under exponential-family noise, which generalizes the standard settings such as Gaussian and Poisson tensor completion. To handle exponential-family tensor completion, we propose a family of dual-TV (DTV) regularizers based on the transformed L1 function, which simultaneously capture sparsity and low-rank structures in the gradient tensor. Moreover, we establish the theoretical upper bounds on the recovery error of the proposed estimator. In certain cases, these upper bounds can attain the convergence order of $\mathcal{O}\mathbf{(}\boldsymbol{n}_{\mathbf {3}}\boldsymbol{r}_{\boldsymbol{t}}\mathbf{(}\mathbf{max}_{\boldsymbol{k}}\boldsymbol{s}_{\boldsymbol{k}}^{\mathbf 2}\mathbf{)}\mathbf{log}\mathbf{((}\boldsymbol{n}_{\mathbf 1}+\boldsymbol{n}_{\mathbf 2})\boldsymbol{n}_{\mathbf 3}\mathbf{)}/\boldsymbol{n}\mathbf{)}$, and the minimax lower bound analysis is further presented to show that the upper-bounds can approach the lower bound with the gap of order $\mathcal{O}\mathbf{(}\mathbf{max}_{\boldsymbol{k}}\boldsymbol{s}_{\boldsymbol{k}}^{\mathbf 2}\mathbf{/}\boldsymbol{max}\mathbf{(}\boldsymbol{n}_{\mathbf 1},\boldsymbol{n}_{\mathbf 2}\mathbf{))}$ up to a logarithmic factor. Finally, multiple groups of experiments on synthetic, image and video tensor data sets are conducted to support our theoretical results and demonstrate the effectiveness of our method.
Förderung
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Cao, W., Chen, Y., Zhao, Q., Li, J., & Cichocki, A. (2026). Exponential-Family Tensor Completion via Nonconvex Dual Total-Variation Regularization. IEEE Transactions on Signal Processing, 74, 3346-3361. https://doi.org/10.1109/tsp.2026.3716059
Vancouver
Cao W, Chen Y, Zhao Q, Li J, Cichocki A. Exponential-Family Tensor Completion via Nonconvex Dual Total-Variation Regularization. IEEE Transactions on Signal Processing. 2026;74:3346-3361. doi:10.1109/tsp.2026.3716059
BibTeX
@article{Cao2026,
author = {Cao, Wenfei and Chen, Yang and Zhao, Qibin and Li, Jinglai and Cichocki, Andrzej},
title = {Exponential-Family Tensor Completion via Nonconvex Dual Total-Variation Regularization},
journal = {IEEE Transactions on Signal Processing},
year = {2026},
volume = {74},
pages = {3346--3361},
doi = {10.1109/tsp.2026.3716059}
}
EUVIMED