Research map / Learning theory and algorithms / Matrix and tensor methods
Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use tensor tubal rank and the t-SVD tensor nuclear norm rather than processing color channels independently | TRPCA · 50 Berkeley color images with 10% of pixels corrupted | PSNR | Helped |
| Use tensor structure across channels rather than independent channel-wise matrix recovery | TRPCA vs RPCA · 50 Berkeley color images with 10% of pixels corrupted | PSNR | Helped |
| Use the tensor nuclear norm model instead of the SNN model | TRPCA vs SNN · 50 Berkeley color images with 10% of pixels corrupted | PSNR | Helped |
| Set λ to 1/√(n(1)n3) rather than tuning it more carefully | TRPCA · Color image denoising | PSNR | Mixed |
| Recover face-image tensors with random pixel corruption using the theoretical λ | TRPCA · Extended Yale B face images | visual denoising quality | Helped |
| Solve the low-tubal-rank plus sparse-error decomposition with the convex TRPCA program | TRPCA · Random tensors with 10% and 20% sparse errors | relative reconstruction error | Helped |
Closest papers by meaning
- Fast and Provable Nonconvex Tensor RPCA (ICML 2022 · similarity 0.94)
- Outlier-Robust Tensor PCA (CVPR 2017 · similarity 0.93)
- The Complexity of Sparse Tensor PCA (NeurIPS 2021 · similarity 0.91)
- Robust High-Order Tensor Compressive Sensing Based on M-Estimators (AAAI 2026 · similarity 0.90)
- Low-Rank Tensor Completion With a New Tensor Nuclear Norm Induced by Invertible Linear Transforms (CVPR 2019 · similarity 0.89)
- Towards Multi-Mode Outlier Robust Tensor Ring Decomposition (AAAI 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.