Researchers have developed a new theoretical framework for tensor completion using dual-total variation (DTV) regularization. This method is designed to handle exponential-family noise, which encompasses common distributions like Gaussian and Poisson. The proposed DTV regularizers capture both sparsity and low-rank structures in gradient tensors, and the study establishes theoretical upper bounds on recovery error that approach minimax lower bounds. Experiments on synthetic, image, and video data demonstrate the effectiveness of this approach. AI
RANK_REASON The cluster contains an academic paper detailing a new statistical methodology. [lever_c_demoted from research: ic=2 ai=0.4]
- alphaXiv
- arXiv
- arXivLabs
- CatalyzeX Code Finder for Papers
- Connected Papers
- DagsHub
- Gaussian
- Gotit.pub
- Hugging Face
- Influence Flower
- Litmaps
- Poisson
- ScienceCast
- scite Smart Citations
- total variation
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
